1.Innovative tools for detection of plant pathogenic viruses and bacteria by Mara M.

Lo pez Edson Bertolini, Antonio Olmos Paola Caruso, Mara Teresa Gorris Pablo
Llop, Ramo n Penyalver Mariano Cambra
This work proposed that detection of harmful viruses and bacteria in plant material,
vectors or natural reservoirs is essential to ensure safe and sustainable agriculture. The
techniques available have evolved significantly in the last few years to achieve rapid and
reliable detection of pathogens, extraction of the target from the sample being important for
optimising detection. For viruses, sample preparation has been simplified by imprinting or
squashing plant material or insect vectors onto membranes. To improve the sensitivity of
techniques for bacterial detection, a prior enrichment step in liquid or solid medium is
advised. Serological and molecular techniques are currently the most appropriate when high
numbers of samples need to be analysed. Specific monoclonal and/or recombinant antibodies
are available for many plant pathogens and have contributed to the specificity of serological
detection. Molecular detection can be optimised through the automatic purification of nucleic
acids from pathogens by columns or robotics. New variants of PCR, such as simple or
multiplex nested PCR in a single closed tube, co-operative- PCR and real-time monitoring of
amplicons or quantitative PCR, allow high sensitivity in the detection of one or several
pathogens in a single assay. The latest development in the analysis of nucleic acids is
microarray technology, but it requires generic DNA/RNA extraction and pre-amplification
methods to increase detection sensitivity. The advances in research that will result from the
sequencing of many plant pathogen genomes, especially now in the era of proteomics,
represent a new source of information for the future development of sensitive and specific
detection techniques for these microorganisms. Plant pathogenic viruses and bacteria are
responsible for increasing economic losses worldwide. They can cause a large range of
symptoms in most cultivated plants, which can be affected in their different parts with various
agronomic impact. Viruses and bacteria cause plant diseases that are difficult to control
because of the lack of efficient products for chemical treatment under field conditions.
Consequently, preventive measures to avoid planting of contaminated material are of the
highest importance in the context of an integrated approach to control. Among such
measures, testing of planting material for pathogen-free status is an important, although not
exclusive, method for controlling bacterial and viral diseases of plants . As many pathogenic
viruses and bacteria remain latent in the planting material, and in very low numbers, methods
of high sensitivity, specificity and reliability are required. Public institutions and the agrofood industry used to control the sanitary quality of seeds, fruits and plant material by
microbiological testing for bacteria and biological indexing for viruses. These methods were
often expensive and time-consuming and some of them were not sensitive and specific
enough. In addition, biological indexing cannot be applied on the large scale required. The
panel of techniques for rapid, specific, and sensitive detection of plant pathogenic viruses and
bacteria has improved and increased in the last few years. To reach higher sensitivity in
serological or molecular detection, two complementary strategies can be applied:
amplification of the target and/or amplification of the signal. The pathogen or target
amplification or enrichment can be carried out in vivo (in planta) or in vitro, preferentially
with selective media and at the optimum growing conditions for each pathogen, or by
molecular techniques including PCR. Signal amplification can be obtained by chemical,
molecular or electronic methods. Among molecular techniques, multiplex PCR is
increasingly used because it improves the efficiency of diagnostic PCR . In the near future
multiplex PCR will probably be adapted for the simultaneous detection of viruses and
bacteria of one particular crop and for the simultaneous detection of other major plant

pathogens such as viruses, viroids, bacteria, and fungi in the same reaction, as already
demonstrated for viruses and viroids or viruses and bacteria. The future will bring more novel
Issues
Noise interrupt output
High sensitivity detection is more complicated

2. Simultaneous detection and identification of the Xanthomonas species complex

associated with tomato bacterial spot using species-specific primers and multiplex PCR
by E.R. Arau jo, J.R. Costa, M.A.S.V. Ferreira1 and A.M. Quezado-Duval
This work establish protocols for the simultaneous detection and identification of
Xanthomonas species causing tomato bacterial spot. The work verified the specificity and
sensitivity of the previously reported sets of primers designed for strains of the four species
of Brazilian tomato bacterial spot xanthomonads, consisting of 30 of Xanthomonas
euvesicatoria, 30 of X. vesicatoria, 50 of X. perforans and 50 of X. gardneri. Furthermore, the
work tested a multiplex PCR protocol for the purpose of concurrent species identification.
The possibility of direct detection of the pathogens in diseased leaf samples was also verified.
The primers were highly specific, amplifying only target DNA. The sensitivity of the primers
in conventional PCR was 50 pg ll _1 for purified DNA and ranged from 5 9 102 to 5 9 104
CFU ml _1 when bacterial suspensions were analysed. The multiplex PCR was suitable for
the detection of all four species and showed similar sensitivity to conventional PCR when
tested on purified DNA. When using bacterial suspensions, its sensitivity was similar to
conventional PCR only when a biological amplification step (Bio-PCR) was included. Both
methods were able to detect the pathogens in symptomatic tomato leaves. Brazilian
Xanthomonas strains causing tomato bacterial spot can be differentiated and identified at
species level by a PCR-based method and by a multiplex PCR. Significance and Impact of
the Study: This protocol may be a feasible alternative tool for the identification and detection
of these pathogens in plant material and may be used for routine diagnostic purposes in plant
pathology laboratories. A complex of species of the genus Xanthomonas are causal agents of
tomato bacterial spot, namely X. euvesicatoria, X. vesicatoria, X. perforans and X. gardneri
Bacterial spot has a worldwide occurrence and can be found on all aerial parts of the plant.
Yield reduction because of the disease is a result of the direct effect on the photosynthetic leaf
area, the drop of buds
Issues
Unstability accuracy
Complicate to develop

3. A review of advanced techniques for detecting plant diseases by Sindhuja Sankarana,

Ashish Mishraa, Reza Ehsania, , Cristina Davi
This work propose that diseases in plants cause major production and economic losses
in agricultural industry worldwide. Monitoring of health and detection of diseases in plants
and trees is critical for sustainable agriculture. To the best of our knowledge, there is no
sensor commercially available for real-time assessment of health conditions in trees.
Currently, scouting is most widely used mechanism for monitoring stress in trees, which is an
expensive, labor-intensive, and time-consuming process. Molecular techniques such as
polymerase chain reaction are used for the identification of plant diseases that require
detailed sampling and processing procedure. Early information on crop health and disease
detection can facilitate the control of diseases through proper management strategies such as
vector control through pesticide applications, fungicide applications, and disease-specific
chemical applications; and can improve productivity. The present review recognizes the need
for developing a rapid, cost-effective, and reliable health monitoring sensor that would
facilitate advancements in agriculture. It describes the currently used technologies that can be
used for developing a ground-based sensor system to assist in monitoring health and diseases
in plants under field conditions. These technologies include spectroscopic and imaging based,
and volatile profiling-based plant disease detection methods. The work compares the benefits
and limitations of these potential methods. It is feasible to incorporate the imaging and VOC
profiling techniques into an autonomous robot as these techniques are well established for
other industrial applications. Once these techniques are well established for a specific disease
detection application, these methods can be integrated with an autonomous agricultural
vehicle for real-time monitoring for plant diseases. Recent reports in the literature support the
notion that both volatile profiling and changes in spectral reflectance can be used for noninvasive field monitoring of plant diseases. Plants and trees release volatile organic
compounds (VOCs) as a result of the metabolic activities taking place within its shoots,
leaves, flowers, or fruits. The VOC profile of each plant differs significantly based on its
physiological condition and the species. Various factors influence the profile of VOCs from a
particular plant or tree, which may include changes in plant metabolism as a result of
environmental changes, the age of plant, developmental stage of a plant, effect of stress on
plants, and the presence of disease/herbivore in a plant. The present work reviews and
summarizes some of the non-invasive techniques that have been used for plant disease
detection. The two major categories for non-invasive monitoring of plant diseases are:(i)
spectroscopic and imaging techniques, and (ii) volatile organic compounds profiling-based
technique for recognizing plant diseases. The spectroscopic and imaging techniques include
fluorescence spectroscopy, visible-IR spectroscopy, fluorescence imaging, and hyperspectral
imaging. The VOC profile-based disease detection involves using electronic nose or GCMS
based volatile metabolite analysis released by healthy and diseased plants as a tool for
identifying diseases. Some of the challenges in these techniques are: (i) the effect of
background data in the resulting profile or data, (ii) optimization of the technique for a
specific plant/tree and disease, and (iii) automation of the technique for continuous automated
monitoring of plant diseases under real world field conditions. The review suggests that these
methods of disease detection show a good potential with an ability to detect plant diseases
accurately. The spectroscopic and imaging technology could be integrated with an
autonomous agricultural vehicle for reliable and real-time plant disease detection to achieve
superior plant disease control and management.

Issues
Undetermained accuracy boundary
Complicate to develop in real time

4 Digital image processing techniques for detecting, quantifying and classifying plant
diseases by Jayme Garcia Arnal Barbedo
This woek propose a survey on methods that use digital image processing techniques
to detect, quantify and classify plant diseases from digital images in the visible spectrum.
Although disease symptoms can manifest in any part of the plant, only methods that explore
visible symptoms in leaves and stems were considered. This was done for two main reasons:
to limit the length of the work and because methods dealing with roots, seeds and fruits have
some peculiarities that would warrant a specific survey. The selected proposals are divided
into three classes according to their objective: detection, severity quantification, and
classification. Each of those classes, in turn, are subdivided according to the main technical
solution used in the algorithm. This work is expected to be useful to researchers working both
on vegetable pathology and pattern recognition, providing a comprehensive and accessible
overview of this important field of research. Agriculture has become much more than simply
a means to feed ever growing populations. Plants have become an important source of energy,
and are a fundamental piece in the puzzle to solve the problem of global warming. There are
several diseases that affect plants with the potential to cause devastating economical, social
and ecological losses. In this context, diagnosing diseases in an accurate and timely way is of
the utmost importance. There are several ways to detect plant pathologies. Some diseases do
not have any visible symptoms associated, or those appear only when it is too late to act. In
those cases, normally some kind of sophisticated analysis, usually by means of powerful
microscopes, is necessary. In other cases, the signs can only be detected in parts of the
electromagnetic spectrum that are not visible to humans. A common approach in this case is
the use of remote sensing techniques that explore multi and hyperspectral image captures.
The methods that adopt this approach often employ digital image processing tools to achieve
their goals. However, due to their many peculiarities and to the extent of the literature on the
subject, they will not be treated in this work The wide-ranging variety of applications on the
subject of counting objects in digital images makes it difficult for someone to prospect all
possible useful ideas present in the literature, which can cause potential solutions for
problematic issues to be missed. In this context, this work tried to present a comprehensive
survey on the subject, aiming at being a starting point for those conducting research on the
issue. Due to the large number of references, the descriptions are short, providing a quick
overview of the ideas underlying each of the solutions. It is important to highlight that the
work on the subject is not limited to what was shown here. Many papers on the subject could
not be included in order to keep the work length under control the papers were selected as
to consider the largest number of different problems as possible. Thus, if the reader wishes to
attain a more complete understanding on a given application or problem, he/she can refer to
the bibliographies of the respective articles.
Issues
Classification boundary mixed with other which make unpredictable output
High loading process

5. A Framework for Detection and Classification of Plant Leaf and Stem Diseases By
Dheeb Al Bashish, Malik Braik, and Sulieman Bani-Ahmad
This work propose and evaluate a framework for detection of plant leaf/stem diseases.
Studies show that relying on pure naked-eye observation of experts to detect such diseases
can be prohibitively expensive, especially in developing countries. Providing fast, automatic,
cheap and accurate image processing- based solutions for that task can be of great realistic
significance. The proposed framework is image-processing basedand is composed of the
following main steps; in the first step the images at hand are segmented using the K-Means
technique, in the second step the segmented images are passed through a pre-trained neural
network. As a testbed, this work use a set of leaf images taken from Al-Ghor area in Jordan.
Our experimental results indicate that the proposed approach can significantly support
accurate and automatic detection of leaf diseases. The developed Neural Network classifier
that is based on statistical classification perform well and could successfully detect and
classify the tested diseases with a precision of around 93%. Plant diseases have turned into a
nightmare as it can cause significant reduction in both quality and quantity of agricultural
products , thus negatively influence the countries that primarily depend on agriculture in its
economy. Consequently, detection of plant diseases is an essential research topic as it may
prove useful in monitoring large fields of crops, and thus automatically detect the symptoms
of diseases as soon as they appear on plant leafs. Monitoring crops for to detecting diseases
plays a key role in successful cultivation. The naked eye observation of experts is the main
approach adopted in practice. However, this requires continuous monitoring of experts which
might be prohibitively expensive in large farms. Further, in some developing countries,
farmers may have to go long distances to contact experts, this makes consulting experts to
very expensive and time consuming . Therefore; looking for a fast, automatic, less expensive
and accurate method to detect plant disease cases is of great realistic significance. Studies
show that image processing can successfully be used as a disease detection mechanism. Since
the late 1970s, computer-based image processing technology applied in the agricultural
engineering research became a common. In this study this work propose and experimentally
validate the significance of using clustering technique and neural networks in automatic
detection of leaf diseases. The proposed approach is image-processing-based and is
composed of the following main steps; in the first step the images at hand are segmented
using the K-Means technique, in the second step the segmented images are passed through a
pre-trained neural network. As a testbed this work use a set of leaf images taken from AlGhor area in Jordan. This work test our program on five diseases which effect on the plants;
they are: Early scorch, Cottony mold, Ashen mold, late scorch, tiny whiteness. Our
experimental results indicate that the proposed approach can significantly support accurate
and automatic detection of leaf diseases. In this work an image-processing-based approach is
proposed and used for leaf and stem disease detection. This work test our program on five
diseases which effect on the plants; they are: Early scorch, Cottony mold, ashen mold, late
scorch, tiny whiteness. The proposed approach is image-processing-based. In the first step of
the proposed approach, the images at hand are segmented using the K-Means technique, in
the second step the segmented images are passed through a pre-trained neural network. As a
testbed this work use a set of leaf images taken from Al-Ghor area in Jordan. Our
experimental results indicate that the proposed approach can significantly support accurate
and automatic detection of leaf diseases. Based on our experiments, the developed Neural

Network classifier that is based on statistical classification perform well and can successfully
detect and classify the tested diseases with a precision of around 93%.
Issues
Filtering method can be implement
Advanced segmentation not used

6. An image-processing based algorithm to automatically identify plant disease visual

symptoms by Camargoa, J.S. Smithb
This work describes an image-processing based method that identifies the visual
symptoms of plant diseases, from an analysis of coloured images. The processing algorithm
developed starts by converting the RGB image of the diseased plant or leaf, into the H, I3a
and I3b colour transformations. The I3a and I3b transformations are developed from a
modification of the original I1I2I3 colour transformation to meet the requirements of the
plant disease data set. The transformed image is then segmented by analysing the distribution
of intensities in a histogram. Rather than using the traditional approach of selecting the local
minimum as the threshold cut-off, the set of local maximums are located and the threshold
cut-off value is determined according to their position in the histogram. This technique is
particularly useful when the target in the image data set is one with a large distribution of
intensities. In tests, once the image was segmented, the extracted region was post-processed
to remove pixel regions not considered part of the target region. This procedure was
accomplished by analysing the neighbourhood of each pixel and the gradient of change
between them. To test the accuracy of the algorithm, manually segmented images were
compared with those segmented automatically. Results showed that the developed algorithm
was able to identify a diseased region even when that region was represented by a wide range
of intensities. The emergence and development of plant diseases and pest outbreaks has
become more common nowadays, as factors such as climate and environmental conditions
are more unsettled than ever. The rate of spread of disease depends on current crop conditions
and susceptibility to infection . When plants become diseased, they can display a range of
symptomssuch as coloured spots, or streaks that can occur on the leaves, stems, and seeds of
the plant. These visual symptoms continuously change their colour, shape and size as the
disease progresses. A banana leaf infected with Black Sigatoka (Mycosphaerella fijiensis
Morelet) at various stages of infection. Stage 1, which is the first external symptom of the
disease. It appears as a small whitish or yellow coloured spot that also resembles the first
stage of the Yellow Sigatoka disease (Mycosphaerella musicola Mulder). These symptoms
can only be observed on the underside of the leaf. In the next stage, stage 2, symptoms appear
as stripes, generally brown in colour and visible on the underside of the leaf,stage 3
symptomsdiffer from stage 2 in that stripes becomes longer, wider and under certain
conditions, such as with weak inoculums and unfavourable climatic conditions, can reach
lengths of 20 or 30mm. Stage 4 symptoms, appear on the underside as a brown spot and on
the upper side as a black spot. Stage 5 is when the elliptical spot is totally black and has
spread to the underside of the leaf. It is surrounded by a yellow halo with the centre
beginning to flatten out. In stage 6, the centre of the spot dries out, turns light grey, and is

surrounded by a well defined black ring which is in turn surrounded by a bright yellow halo.
These spots remain visible after the leaf has dried out, because the ring persists The strategy
for image segmentation described effectively detects and selects the regions that, from the
point of view of a human expert, are considered diseased. The strength of this algorithm is the
ability to identify the correct target (diseased region) in images with different range of
intensities distribution. To justify this statement, the algorithm was tested on a very diverse
set of images and segmentation performance was estimated. Because of the complexity of the
images used in this study, the strategy proposed here may be suitable for other type of images
whose targets are different to that of images showing diseased plants. The next stage of
developing a disease classification system is to extract parameters of the diseased region and
classify the image accordingly.
Issues
Taking more memory to process
Consuming more time
7. Classification of Cotton Leaf Spot Disease Using Support Vector Machine By Prof.
Sonal P. Patil1, Ms. Rupali S.Zambre2
This work propose that in order to obtain more value added products, a product quality
control is essentially required Many studies show that quality of agriculture products may be
reduced from many causes. One of the most important factors of such quality plant diseases.
Consequently, minimizing plant diseases allows substantially improving quality of the
productSuitable diagnosis of crop disease in the field is very critical for the increased
production. Foliar is the major important fungal disease of cotton and occurs in all growing
Indian cotton regions. In this work I express Technological Strategies uses mobile captured
symptoms of Cotton Leaf Spot images and categorize the diseases using support vector
machine. The classifier is being trained to achieve intelligent farming, including early
detection of disease in the groves, selective fungicide application, etc. This proposed work is
based on Segmentation techniques in which, the captured images are processed for
enrichment first. Then texture and color Feature extraction techniques are used to extract
features such as boundary, shape, color and texture for the disease spots to recognize
diseases. India is known as agricultural country where large percentage of the population
depends on agriculture. The farming of different crops for optimum yield and quality product
is highly important. It can be improved with the help of technological support. India is the
important cotton growing country. Many states in India grows cotton. Cotton is also known
as" The White Gold" or the "emperor Fibers" enjoys a most excellent status among all cash
crops in the country. It provides livelihood to about sixty million people and is an important
agricultural commodity providing remunerative income to millions of farmers both in
developed and developing countries. The world textile industries require cotton. India thus
enjoys the distinction of being the earliest country in the world to domesticate cotton and
utilize its fibre to manufacture fabric. The main cause for the disease is the leaf of the cotton
plant. About 80 % of disease on the cotton plant is on its leaves. Therefore our study of
interest is the leaf of the cotton tree rather than whole cotton plant the cotton leaf is mainly
suffered from diseases like fungus, Foliar leaf spot of cotton,. The machine vision system
now a day is normally consists of computer, digital camera and application software. Image
recognition has attracted many researchers in the area of pattern recognition, similar flow of
ideas are applied to the field of pattern recognition of plant leaves, that is used in diagnosing

the cotton leaf diseases. This work know that observation of the human eye is not so strong
that he can the infected part of image because that minute variation pattern of color can be a
different disease present on the leaf of cotton. Our software can provide the exactly
differentiate the difference of color present on these leaves and depending upon that
difference the further compare with database stored image features related to the color. This
work consists of identifying the affected part of the disease. Cotton leaf spot disease spots
were segmented efficiently according to color and outline of disease spots. Initially Image
segmentation is done, and finally image analysis and important features are extracted and
classification of diseases is performed using SVM classifier.
Issues
Accuracy is low
More number of features

8. Color Transform Based Approach for Disease Spot Detection on Plant Leaf By Piyush
Chaudhary1, Anand K. Chaudhari2, Dr. A. N. Cheeran3 and Sharda Godara4
In this work, an algorithm for disease spot segmentation using image processing
techniques in plant leaf is implemented. This is the first and important phase for automatic
detection and classification of plant diseases. Disease spots are different in color but not in
intensity, in comparison with plant leaf color. So this work color transform of RGB image can
be used for better segmentation of disease spots. In this work a comparison of the effect of
CIELAB, HSI and YCbCr color space in the process of disease spot detection is done.
Median filter is used for image smoothing. Finally threshold can be calculated by applying
Otsu method on color component to detect the disease spot. An algorithm which is
independent of background noise, plant type and disease spot color was developed and
experiments were carried out on different Monocot and Dicot family plant leaves with
both, noise free (white) and noisy background. Some researchers have used image processing
techniques for fast and accurate detection of plant diseases . The steps followed by these
researchers in detection of leaf spot diseases are: image acquisition, image pre-processing,
disease spot segmentation, feature extraction and disease classification. The accuracy of
result depends on method used for disease spot detection. The main obstacle in disease spot
detection is noise, which is introduced by camera flash, change in illumination, noisy
background and presence of vein in the plant leaf. Therefore a method which wipes out the
noise and provides better disease spot segmentation is needed Nunik Noviana Kurniawati et
al introduced a method for detection and classification of paddy disease. In this method Otsu
threshold is used for disease spot detection and unnecessary spots are removed using median
filter. Geng Ying et al studied the method of image pre-processing for detecting the disease
spot. In this work median filter is used for image smoothing. Threshold technique is used to
convert filtered image into binary image and finally using edge detection technique, disease
spot is detected. Using above techniques disease spot can be detected in Monocot family
plants, in which mostly veins are parallel and less visible. Problem occurs when the same
technique is applied on Dicot family plants to detect the disease spot, in which veins form a

netted pattern. In dicot plant leaves, larger veins are thicker and straighter . In the process of
disease spot detection disturbance mainly occurs because of these thicker veins. Veins color is
same as plant leaf color only intensity differs. On the other hand, disease spot color is
different from plant leaf color. So first if image is transformed from device dependent color
space to device independent color space and threshold is applied on color component, one
can get better detection of disease spot. Some researchers first convert RGB image into Hue
Saturation Intensity (HSI) model and then apply threshold on H component for segmenting
infected areas from plant leaves. Di Cui et al developed a fast manual threshold-setting
method based on HSI color model to segment the disease spot . Song Kai et al convert RGB
image into YCbCr color space to detect the disease spot. In this work YCbCr, HSI and
CIELAB color models are studied. All these color models are compared and finally A
component of CIELAB color model is used. Color transformed image is passed through
median filter. In last, disease spots are segmented by applying OTSU threshold on A
component of LAB color space. Experimental result shows that noise which is introduced
because of background, vein and camera flash; can be wiped out using CIELAB color
model . Following this method different disease spots are detected accurately and results are
not affected by background, type of leaf, type of disease spot and camera. Further to this it is
needed to compute disease spot area for assessment of loss in agriculture crop. Disease can be
classified by calculating dimensions of disease spot. In this work veins having color similar
to the spot is not considered. Further work need to be carried out in those lines also.
Issues
Segmentation performance have to be improve
Accuracy decreases while increase training datasets

9 LEAF DISEASE SEVERITY MEASUREMENT USING IMAGE PROCESSING By

Sanjay B. Patil1, Dr. Shrikant K. Bodhe2
This wok propose that Fungi-caused diseases in sugarcane are the most predominant
diseases which appear as spots on the leaves. If not treated on time, causes the severe loss.
Excessive use of pesticide for plant diseases treatment increases the cost and environmental
pollution so their use must be minimized. This can be achieved by targeting the diseases
places, with the appropriate quantity and concentration of pesticide by estimating disease
severity using image processing technique. Simple threshold and Triangle thresholding
methods are used to segment the leaf area and lesion region area respectively. Finally
diseases are catcogrise by calculating the quotient of lesion area and leaf area. The accuracy
of the experiment is found to be 98.60 %. Research indicates that this method to calculate leaf
disease severity is fast and accurate. Sugarcane being a long duration crop of 10 to 18
months, attacked by a number of diseases. Fungi caused diseases in sugarcane are the most
predominant diseases which appear as spots on the leaves. These spots prevent the vital
process of photosynthesis to take place, hence to a large extent affects the growth and
consequently the yield. In case of severe infection, the leaf becomes totally covered with
spots. The various types of diseases on sugarcane determine the quality, quantity, and stability
of yield. The diseases in sugarcane not only reduce the yield but also deteriorate of the variety
and its withdrawal from cultivation. Excessive uses of pesticide for plant diseases treatment

increases the danger of toxic residue level on agricultural products and has been identified as
a major contributor to ground water contamination also pesticides are among the highest
components in the production cost their use must be minimized. This can be achieved by
estimating severity of disease and target the diseases places, with the appropriate quantity and
concentration of pesticide. The naked eye observation method is generally used to decide
diseases severity in the production practice but results are subjective and it is not possible to
measure the disease extent precisely. Grid counting method can be used to improve the
accuracy but this method has cumbersome operation process and time consuming. Image
processing technology in the agricultural research has made significant development. To
recognize and classify sugarcane fungi disease an automated system has been implemented
using algorithm such as chain code technique, bounding box method and moment analysis.To
measure severity of Rust disease on Soybean, disease spot have segmented by Sobel operator
to find out spot edge and plant disease severity has measured by calculating the quotient of
disease spot area and leaf area.Earlier severity of attack of herbivorous insects on leaves have
been calculated using video digitizer for pesticide application.Extent of color patches due to
micronutrient deficiency or fungal disease on leaves have calculated by color thresholding
method .In particular disease color as well as shape of leaves also changes that have
measured by using HSV color space, Speeded Up Robust Features (SUFR), Scale Invariant
and Feature Transformation (SIFT).By choosing color difference due to fungal infection and
lookup table it is possible to distinguish the healthy leaf area from diseased one.Disease
severity can be measured in three different ways that are Visual Rating, Image Analysis and
Hyper spectral Imaging.Using multispectral images thresholding operation Ratio of Infected
Area (RIA), Lesion Color Index (LCI) and Severity Index of Soybean rust have been
calculated.Similarly using reflectance value in the green and NIR regions, same time the
SWIR domains, orange rust of sugarcane has detected.These spectral reflectance value is also
useful to determine chlorophyll index which is helpful for sugarcane infected plots detection
and monitoring from Satellite imagery.Disease in wheat plant has detected in early stage
using spectral reflectance of plant and neural network.Disease infection on fruits is also
important to maintain the quality of the fruit, to increase the final yield. Many research have
been conducted for the same as - classification of grape fruit peel disease have been done
using color texture feature sets through a discriminate function with 2.3 % standard deviation.
Classification of Citrus disease also carried out using feature and classification using neural
network based back propagation algorithm. In this research severity of brown spot disease is
measured with the help of image processing technique. Brown spot causes reddish-brown to
dark-brown spots on sugarcane leaves. The spots are oval in shape, often surrounded by a
yellow halo and are equally visible on both sides of the leaf. The long axis of the spot is
usually parallel to the midrib. The accuracy of the algorithm is tested by estimating the
percentage standard known area covered by standard known area shapes like Triangle, Circle,
Square, and Rectangle drawn by using a tool such as paint which comes as accessories of
Microsoft Windows Operating System. Estimated values are compared with actual area
covered to calculate Percentage Deviation (D) and Percentage Accuracy of the algorithm.
Disease symptoms of the plant vary significantly under the different stages of the disease so
to the accuracy with which the severity of the disease measured is depends upon
segmentation of the image. Simple threshold segmentation is used to calculate the leaf area
but this method is not suitable to calculate the area of the lesion region because of varying
characteristics of the lesion region. Triangle method of the thresholding used here to segment
the lesion region. The average accuracy of the experiment is 98.60 %. Thus image processing
technology to measure plant disease severity is convenient and accurate. This eliminates
subjectivity of traditional methods and human induced errors. It will helps to farmers to

decide the specific quantity for pesticide application which reduces the cost and
environmental pollution
Issues
Concept is complicate to understand
Real time un predictable accuracy
10. Automated rice leaf disease detection using color image analysis by Reinald Adrian
DL. Pugoya, Vladimir Y. Marianoa
This work describe that in rice-related institutions such as the International Rice
Research Institute, assessing the health condition of a rice plant through its leaves, which is
usually done as a manual eyeball exercise, is important to come up with good nutrient and
disease management strategies. In this work, an automated system that can detect diseases
present in a rice leaf using color image analysis is presented. In the system, the outlier region
is first obtained from a rice leaf image to be tested using histogram intersection between the
test and healthy rice leaf images. Upon obtaining the outlier, it is then subjected to a
threshold-based K-means clustering algorithm to group related regions into One of the
worlds most important food crops is rice. It serves as staple food for almost half of the
worlds population. The demand for rice increases, as food and population also continue to
increase. There is a need to increase rice yield to cope with the worlds growing population.
According to Dobermann and Fairhust, the main agronomic problems encountered in rice
cultivation are reduced yield caused by pests, poor management of input, uneven use of
nutrients, ineffective use of irrigated water, and degradation of the environment. Furthermore,
some of these problems may even lead to other problems. The uneven use of nutrients, due to
improper fertilizer application, eventually leads to poor plant health. Consequently, this
increases the chances of plants to pests and diseases susceptibility. These problems result to
significant decrease in rice yield and quality. The attainment of the goal of coping with the
increasing demand for rice is therefore hindered. Symptoms of diseases are usually
manifested in rice leaves. By analyzing the appearance of rice leaves, one can determine the
disease present in the rice plant. These symptoms show different size and shape of
discoloration in a certain part of the leaf, such as a spot which is a localized necrotic area, and
a lesion, a localized area of discoloured tissue. At present, assessment of plant health through
the leaves is usually done as a manual eyeball exercise. Manual assessment depends on the
person screening the leaf, thus, this method is subjective, cumbersome and prone to errors. In
this study, the disease detection process is automated using color image analysis. In the image
analysis system, a rice leaf image is subjected basically to color clustering to find major
colors in the leaf. The information derived would then be further analyzed to determine which
disease is present, whether a brown spot or a leaf scald, two of the most important fungal
diseases in rice. A brown spot is characterized by oval shaped region, a shape similar to a
sesame seed. On the other hand, a leaf scald can be described as an oblong or diamondshaped lesion which is larger than a brown spot. Nevertheless, automation eliminates
subjectivity, and makes the work less tedious and time-consuming. Accuracy, precision and
consistency improve since each sample leaf undergoes the same process. This study is done
in collaboration with IRRI. First, the system is able to identify areas which contain
abnormalities. Histogram intersection has been useful to isolate outlier region. Second, a
threshold-based clustering algorithm helps in separating the outlier region into different
clusters, where each cluster contain colors related with one another. For future studies, it is

important to check and observe the threshold to be used in the said algorithm. Lastly, the
system is also able to assess and determine suspected diseases which infected the rice leaf by
comparing and matching colors. This system is very applicable for those diseases with
symptoms that are based on colors only. But there are also diseases with symptoms that are
also based on shape or location of a particular region in the rice leaf image. In this very
reason, to make the system more reliable, accurate and powerful, shape and spatial analysis
shall also be incorporated for further observation and studies
Issues
This system is very applicable for those diseases with symptoms that are based on
colors only
Threshold-based output

11. Diagnosis of bacterial spot of tomato using spectral signatures byC.D. Jonesa, J.B.
Jonesb, W.S. Leea
This work says that Ultraviolet, visible, and near-infrared reflectance spectroscopy
was used to determine the disease severity of tomato (Lycopersicon esculentum) leaves
infected with Xanthomonas perforans, the causal agent of bacterial leaf spot of tomato.
Chemometric methods were used to identify significant wavelengths and create spectralbased prediction models. Significant wavelengths were identified through analysis of the Bmatrix from partial least squares (PLS) regression, analysis of a correlation coefficient
spectrum, and through the use of a stepwise multiple linear regression (SMLR) procedure.
These analysis methods revealed several significant regions wavelengths and produced
predictive models of disease severity based on absorbance spectra. The best model predicted
the disease severity of the validation data set with a root mean square difference (RMSD) of
4.9% and a coefficient of determination (R2) of 0.82. The results of this initial study indicate
the potential for the use of spectral technology to detect bacterial leaf spot of tomato in the
field. Tomato (Lycopersicon esculentum) is an important commodity in Florida. Despite the
high productivity of the State in this market, the high humidity, warm temperatures, and high
rainfall rates typical for Florida make crops particularly susceptible to bacterial spot disease.
The disease affects all aboveground plant parts, but is most noticeable as spots on leaves and
fruit. It has beenshown to be endemic and has been demonstrated to cause severe reduction in
marketable fruit yield. Currently, treatments for bacterial spot do exist. Copper bactericide
and bacteriophage applications have been shown to reduce incidence of bacterial spot
effectively, and these treatments have been shown to be economically beneficial to
growers.Despite these available proven applications, many fields remain significantly
affected. This is because current methods of disease detection in many cases are inadequate
Assessment of crop disease damage is typically determined using field scouting, which has
been shown to be expensive, time-consuming, and difficult for large farms. Field scouting is
usually conducted on a weekly interval, and treatments are applied if disease is detected. For
large-scale operations, however, conventional ground scouting has been shown to be
incapable of providing efficient disease monitoring in an economical manner. Remote sensing
has the potential to detect crop diseases for large scale operations in a rapid and spatially
specific manner . Early and accurate diagnosis of bacterial spot in the field could enhance the
ability of farmers to implement beneficial disease treatments in an economical manner,
reducing the incidence of disease, the amount of chemical applications, the cost of these

chemical applications, and the monitoring cost. This approach could also be useful to
researchers for determining the effectiveness of chemical control strategies by allowing more
accurate and quantitative disease assessment. This study was conducted in order to identify
the spectral signatures of tomatoes infected with bacterial leaf spot and to create disease
prediction models based on these spectral responses. A laboratory spectrophotometer was
used to collect diffuse reflectance measurements of leaf samples of varying degrees of
infection. Acorrelation coefficient spectrum, PLS regression, and SMLR procedure were used
to identify important wavelengths and create predictive models. Wavelengths around 750
760nm were identified as significant using all approaches and seem highly related to the
disease. Previous studies have shown this region to be significantly influenced by many plant
diseases. Additionally, wavelength 395nm selected by Method 2matches with peaks in the Bmatrix and correlation coefficient spectrum and wavelengths 633635nm identified by
Methods 2 and 3 correspond with a peak in the correlation coefficient spectrum. Wavelengths
around 630nm were previously identified as being significant for detecting yellow rust in
wheat. Wavelengths around 400nm were also previously identified as significant in
determining Colletotrichum orbiculare fungus infection on cucumber. These wavelengths
could also be important for prediction of bacterial leaf spot of tomato disease prediction. The
identification of significant wavelengths at multiple regions of the spectrum is reasonable,
and expected as plant diseases typically affect leaf optical properties at many wavelengths.
Both the SMLR and PLS procedures were able to predict the disease severity well. The PLS
procedure was better suited for handling handling the full absorbance spectra than the SMLR
procedure, with Method 1 predicting disease in the validation dataset with an R2 of 0.77 and
RMSD of 5.6% compared to the R2 of 0.69 and RMSD of 6.4% by Method 2. This is
consistent with results of Min and Lee. The best predictions were made by the SMLR
procedure using absorbance spectra reduced based on B-value. This method predicted disease
with an R2 of 0.82 and RMSD of 4.9%. This study demonstrates it is possible to use spectral
measurements to determine the severity of bacterial spot of tomato infection. This is the first
step in the practical implementation of an improved disease monitoring system. Remote
sensing techniques could next be used to collect absorbance data from large fields. For
example, currently airborne or satellite hyperspectral images are available. A PLS or SMLR
algorithm could be applied to this data to identify areas of infection. This capability would
allow the creation of prescription maps recommending the locations where bacteriophage or
copper bactericide applications should be applied. Such a tool could reduce disease incidence
as well as ensure treatments are applied only to areas of the field in need of treatment.
Issues
Sometime Identifing non important wavelengths changes the output
More number of features

12. Identification of defence metabolites in tomato plants infected by the bacterial

pathogen Pseudomonas syringae by Mara Pilar Lpez-Gresa, Cristina Torres, Laura
Campos, Purificacin Lisn, Ismael Rodrigo, Jos Mara Bells, Vicente Conejero
In the present work, which aimed to define the chemical nature of the
phenylpropanoids induced during the interaction of the tomato plant, cultivar Rutgers, with
the bacterial pathogen Pseudomonas syringae pv. tomato. Using LCMS and NMR
spectroscopy, this work determined the chemical structures of this class of metabolites, which

accumulated in response to exposure to the pathogen. A rapid accumulation of phytoalexin

hydroxycinnamic
acid
amides
(HCAA)
of
noradrenaline
(cis/trans
N-pcoumaroylnoradrenaline and cis/trans N-feruloylnoradrenline) and octopamine (cis/trans N-pcoumaroyloctopamine and cis/trans N-feruloyloctopamine), chlorogenic acid (CGA), and the
flavonoid rutin was detected after bacterial infiltration. Among them, cis N-pcoumaroylnoradrenaline, cis N-p-coumaroyloctopamine, and isomers cis/trans of Nferuloylnoradrenaline have never been described in the literature. Moreover, cis/trans isomers
of N-feruloyloctopamine are identified for the first time as being associated with the
tomato/P. syringae interaction. Inhibition of the P. syringae-induced ethylene by 2aminoethoxyvinylglycine, markedly impaired the accumulation of HCAA in inoculated
tomato leaves, but it had no effect on CGA or rutin synthesis. On the other hand, the lack of
accumulation of SA in NahG transgenic tomato plants, overexpressing a bacterial salicylic
hydroxylase, did not prevent the enhancing of HCAA produced by P. syringae infection.
Taken together, our results indicate that ethylene, but not SA, is essential for the synthesis of
HCAA in response to bacterial infection of tomato leaves. Antibiotic activities of the induced
metabolites were also studied. CGA induced a notable expression of the defence-related
genes PR1 and P23. Moreover, trans-HCAA of noradrenaline and octopamine showed a
potent free radical scavenging competence. In particular, trans N-feruloylnoradrenaline
presented a very outstanding antioxidant activity, thus indicating that these compounds may
play a role in the defence response of tomato plants against bacterial infection. Silica gel
chromatography was performed using pre-coated Merck F254 plates and silica gel 60, 0.06
0.2 mm powder. Optical rotations were measured on a Jasco DIP 370 digital polarimeter. UV
measurements were obtained using a Shimadzu UV-2101PC spectrophotometer. 1H, 13C, and
1H1H COSY NMR spectra were recorded on a Bruker AV 300 MHz instrument.
Multiplicities of 13C signals were assigned by DEPT experiments. For HSQC and HMBC
NMR experiments a Bruker DRX-600 spectrometer, operating at 600 MHz for 1H and 150
MHz for 13C using an inverse TCI CryoProbe fitted with a gradient along the Z-axis, was
used. High resolution ESI-MS data were obtained on a Micromass Q-TOF MicroTM coupled
with a UPLC Aquity. The source parameters of the mass spectrometer for ESI in negative
mode were the following: capillary voltage 3 kV, cone voltage 35 V, extraction cone 0.5 V,
RF Lens1 0.9 V, RF Lens2 6 V, source block temperature 120 C and desolvation gas
temperature 300 C. The desolvation and cone gas used was nitrogen at a flow rate of 650 l
h1 and 50 l h1, respectively. Other mass spectrometer conditions were: low mass
resolution 5, high mass resolution 5, ion energy 0.2, and collision energy 10. ESI data
acquisition was in the conditions of a full scan range from mass-to-charge ratio [m/z] 50
1500 at 0.2 s per scan. The instrument was calibrated using a PEG mixture from 200 to 1500
MW (resolution specification 5000 FWHM, deviation <5 ppm RMS in the presence of a
known lock mass). Induction of potent antioxidants, such as FNA, could constitute a
mechanism of cellular protection to prevent or scavenger the initial burst of reactive oxygen
species upon exposure of tomato leaves to bacteria. Alternatively, accumulation of these
compounds could protect plants acting directly against aspiring new pathogens. In this
context, given the very potent free radical scavenging activity of trans-FNA, it would be
interesting to generate tomato plants with elevated levels of this compound. Following a
similar strategy carried out for THT and tyrosine decarboxylase (TYDC), the two final key
enzymes of HCAA metabolism, work is now in progress to engineer tomato plants with
enhanced activity of both the THT and TYDC enzymes in order to explore whether transFNA accumulates. If this strategy is successful, these transgenic tomato plants would be
useful to investigate the role of trans-FNA in tomatopathogen interaction and as an in vivo
antipathogenic compound.

Issues
More time taken to get better output
Using complicated concepts
13. Outbreaks of Bacterial Spot Caused by Xanthomonas gardnerion Processing
Tomato in Central-By Alice M. Quezado,Caixa ,R. P., Jr., Truffi, D., Daniela Truffi and
Luis E. A. Camargo,
This work present that severe epidemics of bacterial spot have been observed in
central-west Brazil in fields of processing tomato. Several xanthomonads, Xanthomonas
axonopodis pv. vesicatoria, X. vesicatoria, or X. gardneri, can cause the disease; therefore,
attempts were made to identify the pathogen species present in this region. A total of 215
strains were obtained from 10 commercial areas. The strains were characterized using pulsedfield gel electrophoresis (PFGE) and by their amylolytic and pectolytic activities.
Representative strains from each PFGE haplotype then were tested for pathogenicity on
tomato and pepper, carbon source utilization, and whole protein sodium dodecyl sulfate
polyacrylamide gel electrophoresis. rRNA sequence comparisons also were performed. All
strains recovered from six fields were classified as X. gardneri, whereas X. vesicatoria and X.
axonopodis pv. vesicatoria also were detected in the remaining four fields. Strains of X.
gardneri, which could be grouped into two PFGE haplotypes, were unable to hydrolyze starch
and pectate and to utilize gentiobiose and maltose They expressed the protein of 27 kDa
and were pathogenic on tomato but variable on pepper. Processing tomato (Lycopersicon
esculentum Mill.) production areas in Brazil gradually are moving from the southeastern and
northeastern regions towards the central-west, in the states of Gois and Minas Gerais. In this
new agricultural frontier, production increased and represents one-half of the total Brazilian
acreage of processing tomato. Also, the edaphoclimatic conditions are favourable for the
crop, resulting in a superior average yield of 63 t/ha compared with the Brazilian average of
46 t/ha. Bacterial spot, a worldwide important disease of tomato and pepper (Capsicum
annuum L.), has become a major problem in sprinkler-irrigated fields of processing tomato in
Brazil. The disease has the potential to cause heavy yield losses due to its seedborne nature,
the low efficiency of chemical control, and the lack of resistant.This work was supported in
part by CNPq grant 146214/99-4 and FAPESP grant 00/09059-8. Three Xanthomonas spp.
have been shown to cause bacterial spot on tomato and pepper: Xanthomonas axonopodis pv.
vesicatoria, X. vesicatoria, and X. gardneri. The latter was first described in Yugoslavia and
was initially classified as Pseudomonas gardneri. Since then, it had been considered a
synonym of X. vesicatoria . However, the taxonomical status of X. gardneri is still undefined
in spite of being genetically and phenotypically distinct from X. axonopodis pv. vesicatoria
and X. vesicatoria. Thus, this work will refer to this unique population as X. Gardneri for lack
of a universally accepted species name.The criteria used to phenotypically characterize the
Xanthomonas spp. Associated with bacterial spot on tomato include amylolytic and pectolytic
activities, patterns of carbon utilization, serology, fatty acid profiles, silver staining of protein
profiles using sodium dodecyl sulfatepolyacrylamide gel electrophoresis (SDS-PAGE), and
pathogenicity. Also, their genomic structures have been differentiated by analysis of
restriction profiles of hrp genes, pulsed-field electrophoresis (PFGE) of digested genomic
DNA, DNA-DNA reassociation kinetics, repetitive DNA sequence-based polymerase chain
reaction (rep-PCR), and rRNA sequence homology). X. gardneri belongs to group D of the
xanthomonads causing bacterial spot disease on tomato. The bacterium is characterized by its
inability to hydrolyze starch and pectate and to utilize gentiobiose as a source of carbon, a

reaction pattern with a group of monoclonal antibiodies, and the presence of a 27-kDa protein
typical of this group. In addition to the reference strain, originally described in Yugoslavia,
other X. gardneri strains recently were identified in Costa Rica .This work reports the
identification and characterization of strains of X. Gardneri associated with severe outbreaks
of bacterial spot in commercial fields of processing tomato in the central-west region of
Brazil. Classification and haplotypic frequency. Based on the phenotypic and genotypic traits
presented above, strains CNPH496 and CNPH467 were classified as X. gardneri, strain
CNPH411 as X. axonopodis pv. vesicatoria, and CNPH345 as X. vesicatoria. Based on these
species assignments, X. gardneri was the mostprevalent species recovered from all 10 fields;
in 6 fields, it was the only species identified. Of the two X. Gardneri haplotypes, the one
represented by strain CNPH467 was by far the most prevalent (206 of 207 cases). This strain
was deposited in the culture collection of the Instituto Biolgico (Campinas, Brazil) under
IBSBF No. 1782.
Issues
The low polymorphism found among strains could be an indication of a recent
introduction event
This hypothesis is still tentative, because the level of genetic variation within X.
gardneri stills needs to be assessed

14. Detection of Xanthomonas oryzae pv. oryzae in artificially inoculated and naturally
infected rice seeds and plants by molecular techniques by N. Sakthivel C. N.
Mortensen S. B. Mathur
This detection method presents that a polymerase chain reaction (PCR) technique was
developed for detecting the presence of Xanthomonas oryzae pv. oryzae, the bacterial leaf
blight (BLB) pathogen in rice seed and for studying the transmission of this bacterium from
seed to plant. Primers TXT and TXT4R from an insertion sequence (IS1113) of the pathogen
were used to amplify a 964-bp DNA fragment. A combined biological and enzymatic
amplification (BIO-PCR) technique was used to detect the pathogen in naturally infected
seed. The level of detection of TXT and TXT4R primers was 55 fg DNA of X. o. pv. oryzae,
which is roughly the equivalent of seven cells (and four cells in pure culture suspension) of
X. o. pv. oryzae. Hybridization of IS1113 with the amplified DNA fragment in Southern blot
analysis confirmed that the 964-bp DNA fragment was amplified from X. o. pv. oryzae. The
presence of the IS1113 element in strains of X. o. pv. oryzae from 16 rice-growing countries
was confirmed by DNA dot blot analysis. X. o. pv. oryzae was detected from the seed washes
and DNA extracted from the seed washes of naturally infected seeds of cvs Jaya and TN1.
When stored at 4 C, the pathogen was recovered up to4 months and 9 months from naturally
infected seeds of cvs Jaya and TN 1, respectively. The BLB bacterium was also detected in
seedlings, mature plants and seeds collected from plants raised from naturally infected seeds
Our results showed that PCR, BIO-PCR and DNA hybridization techniques could be used to
detect X. o. pv. oryzae in rice seeds and plants. Successful detection based on PCR
techniques depends upon the specificity and sensitivity of primers. Based on the dilution
series of cells, the detection level of TXT and TXT4R primers was 4 cells in a 50 l reaction.
The sensitivity level of these primers was 55 fg of X. o. pv. oryzae DNA. On the basis of the

assumption that the genome size of X. o. pv. oryzae is approximately equivalent to the
genome size of P. fluorescens (7.4103 kb), the 55 fg DNA represented approximately 7
cells. Primers (TXT and TXT4R) used in this study did not amplify DNA from other
pathogenic or saprophytic bacteria of rice, with the exception of X. o. pv. oryzicola, since
IS1113 is also present in X. o. pv. oryzicola. PCR techniques with these primers can be
applicable to detect both pathogens; and pathovars of X. oryzae can be differentiated by
ligation-mediated PCR. Hybridization studies suggest that the 964-bp fragments were
amplified from the IS1113 element of strains of X. o. pv. oryzae from different rice-producing
countries. Therefore, PCR techniques based on TXT and TXT4R primers can be used in
detecting strains of X. o. pv. oryzae with different geographical origins. PCR conditions such
as primers, template, Mg++ , thermocyclers and thermostable polymerase origin have been
shown to affect amplification. In this study, all these parameters were optimized in a Perkin
Elmer 2400 thermocycler to avoid such artifacts and to insure reproducibility of
amplification. Consistent results of amplification of a 964-bp fragment from X. o. pv. oryzae
by TXT and TXT4R were also obtained by using various PCR machines and different Taq
polymerase enzymes supplied A PCR technique was successfully used to detect viable cells
of X. o. pv. oryzae in naturally infected seeds (cv. TN1) up to 8 months from the date of
harvest. Transmission of X. o. pv. oryzae from naturally infected seeds (cvs TN1 and Jaya) to
seedlings was demonstrated. Although PCR is a highly sensitive technique, it
cannotdifferentiate dead cells from live cells. This limitation is of major concern and it affects
PCR application in quarantine laboratories. This problem was solved in an earlier
investigation and in this study, by employing a BIO-PCR technique of plating seed or seed
extract onto agar prior to the application of PCR and using plate-washing (bacteria) as the
template. This method should eliminate the problem of false-negative results due to PCRinhibitors in the plant or seed extracts, if any, and should also avoid false-positive results due
to dead cells. BIO-PCR could be employed without the need for time-consuming DNA
extraction and isolation of X. o. pv. oryzae from seeds. by various manufacturers. The
presence of plant pathogenic bacteria in symptomless plants (latent infection) and the
transmission of bacteria from seed to seed has been documented. Based on our results, the
primers TXT and TXT4R can be used to detect the infection of X. o. pv. oryzae in
symptomless plants. Detection of pathogen in non-symptomatic seedlings is of importance in
certification programs, for both domestic and international quarantine, because a latent
population can lead to serious epidemics under favourable conditions. Early detection of
diseases, using rapid methods, is important for assessing the health status of a rice nursery
before the transplantation of seedlings to fields. In India, general recommendations given to
farmers include the use of seed treatment and prevention measures, including cultural
practices and the production of disease-free nursery plants. Since PCR has the advantage of
detecting the pathogen without the need for pure cultures, this technique should be employed
for the rapid monitoring of pathogenic bacteria in seed lots from commercial seed
consignments and for germplasm- and seed-testing in quarantine laboratories. Considering
the lack of specificity and the amount of work involved in other methods, PCR is a quick,
sensitive technique and should have wide application to detect and study the survival and
transmission of plant pathogenic bacteria. Data generated in this study demonstrate the seedborne nature and transmission of X. o. pv. oryzae, the causal agent of the BLB disease of rice.
Issues
Training Dataset increases decrease the accuracy
Unpredictable chances in validation

15. Near-infrared Spectroscopy in detecting Leaf Miner Damage on Tomato Leaf By

H.R. Xu; Y.B. Ying; X.P. Fu; S.P. Zhu
This work describes that an automatic diagnosis of plant disease is important for plant
management and environmental preservation in the future. The objectives of this study were
to characterise the leaf reflectance spectra of tomato leaves damaged by leaf miner and to
determine which wavelengths were most responsive to plant damage caused by the pest.
Tomato leaf damage was classified into five scales based on the severity levels displayed on
the surfaces of plant leaves. A spectral parameter of reflectance sensitivity was used to find
the optimal wavelengths for determining and evaluating the damage level. Results from nearinfrared spectroscopy showed that there were clear differences in spectral reflectance from
different levels of infestation. Spectral reflectance decreases significantly with the increasing
severity level at the short wavelengths of near infrared 8001100nm but changes for
individual bands of 1450 and 1900nm where spectral reflectance increases with the
increasing severity level. Spectral parameters such as single-wavelength reflectance, peak
area and water band index were used to discriminate the severity level of infestation. The
results indicate that the sensitive bands of 1450 and 1900nm modelled with severity level
provided the highest correlation coefficient Leaf mining, causing succulent leaves to wilt, can
have economic importance. Hosts of the vegetable leaf miner are tomatoes, beans, peas, and
various cucurbits. Any insect that lays its eggs in the spongy layer between the upper and
lower surfaces of leaves is known as a leaf miner. The four stages of its development are: egg,
larva (leaf miner), pupa, and adult (a small fly). Leaf miners develop between the leaf
surfaces and tunnel or mine out the spongy middle layer as they grow, giving leaves a
spotty, brownish appearance and zigzag tunnel, where the small maggots have eaten out the
tissue between the upper and nether surfaces. The leaves of vegetables, fruit, or ornamental
plants are often damaged the most severely by mining. Damage may cover so much of the
leaf that the plant is unable to function, and yields are noticeably decreased. In the past,
chemical sprays have always been used against leaf miners due to their protection within the
plant. However, the layman often confuses leaf miner damage with leaf diseases. Thus, our
objectives were to use spectral reflectance data to determine the SL of leaf damage in
diseased plants and the wavelength bands at which leaf reflectance was most responsive to
tomato leaf damage caused by the pest Leaf-miner infestation on tomato leaves was
successfully determined through laboratory investigation by an optical measurement system
with Fourier transform near-infrared (FT-NIR) systems. In this study, the spectral
characteristics and properties of tomato leaves were that in the short-wavelength near-infrared
(SWNIR) region (8001100 nm), the infested tomato leaves had lower reflectance values
than that of healthy leaves due to the disrupted leaf structure caused by leaf miner, and near
1450 and 1900 nm, with increasing severity of damage, the leaf reflectance increased while
the leaf water content decreased. Using two selected wavebands 1450 and 1900nm and the
spectral parameters such as single wavelength reflectance and peak area, it was possible to
detect successfully the severity level of infestation. A determinate model based on the single
wavelength reflectance at 1450nm showed a good prediction performance (coefficient of
determination R2 0_982). These results are very encouraging for the development of a

cost-effective optical device to determine plant infestation severity. These may improve to
make good use of the pesticide, only applying when and where needed and reducing the
residues in produce and environmental contamination.
Issues
Poor performance but it is good initiative method
It was possibility is minimum to detect successfully the severity level of infestation