Académique Documents
Professionnel Documents
Culture Documents
1. Introduction
1.1 Purpose
1.2 Scope
1.3 Definitions, Acronyms, and Abbreviations
1.4 References
1.5 Overview
3. Specific Requirements
3.6.1 Reliability
3.6.2 Availability
3.6.3 Security
3.6.4 Maintainability
3.6.5 Portability
5. Document Approvals
6. Supporting Information
1. Introduction
1.1 Purpose
In last few years the potential growth in digitization of images has
occurred,with immense amount of information flowing and stored in the
database of world wide web.the No. of users exploiting the WWW has
increased tremendously while accessing and manipulate remotely-stored
images in all kinds of new and exciting ways.However, they are also
discovering that the process of locating a desired image in a large and
varied collection can be a source of considerable frustration.The problems
of image retrieval are becoming widely recognized, and the search for
solutions an increasingly active area for research and development.Some
indication in form of No. of research and development in field of CBIR.No.of
journal articles,research papers, appearing each year on this subject.
1.2 Scope
CBIR usually deals with large image collection of low level and high level
features,which directly influence indexing and retival complexity,memorey
and disk space requirment.due to high memorey and processing power
requirment,cbir has not widely been appplied on platforms having limited
resouces,such as mobile devices
definitions:
Key words:
1.4 References
1.5 Overview
The software product is content based image reteival (CBIR) the complete
search engine that retrieves images based on content like colour
,texture,shape,another image etc.
. Rest of the SRS is organized considering the requirements of multiple
connected systems in mesh architecture. SRS of cbir describes all the
requirements in such a manner that it can be easily understood. It
describes functional as well as non functional requirements. Specific
requirements contains design constraints, data base requirement,
Standards Compliance etc.
2. The Overall Description
● Feature Extractor
● Creates the metadata
● Query Engine
● Calculate similarity
● User Interface
Query engine: this component takes query image as input and sends
image to feature extractor
2.1.2 Interfaces
our system will interact with users with the help of user friendly GUI.
The GUI will be self contained and added with Help function for initial
users.
The content based image retrieval (CBIR) does not require any external
hardware requirements apart from a mouse and keyboard that would
facilitate giving proper inputs in the form of images.
it may also require a scanner to scan external images like medical x-rays .
Matlab 2007-
C#
for devolping GUI of software
version 3.0
Purpose :
Mtalab used for the various feature vector metrics generation for CBIR
SQL SERVER 2007 for Database of images
2.1.7 Operations
Image retrieval is the task of searching for images from an image
database. The query to the
database can be of various types as depicted.
● Query-by-text: The user gives a textual description of the image he is
looking for.
● Query-by-sketch: The user provides a sketch of the image she is
looking for.
● Query-by-example: The user gives an example image similar to the
one he is looking for.
The users are assumed to have basic knowledge of the computers and
Internet browsing.
the cbir is a general purpose application which does not have any specific
user .anybody can efficiently operate the system application.
2.4 Constraints
Hardware limitation: cbir requires large memory requirements
approximately 2 GB
signal timing requirements: the cbir system requires a large processing
time for generating output images.
3. Specific Requirements
The system shall contain
● a browse tool box that will enable the user to select images from his
own personal database,thereby enabling the query by example
feature of CBIR.
the system may contain
● a paint box thereby enabling users to draw the sketches and the
software will search similar images.
the system should contain
● a colour pallette for the users to select specific images based on a
range of colors
● a text based text box which will select all those images tagged with
that particular text .
● a facility that enables multiple selection of the above functions such
as color:red as well as some query image.
3.2 Functions
sequence of operations:
● feature extraction of query image
● image comparision
● image retreival
FEATURE EXTRACTION:
The feature is defined as a function of one or more measurements, each of
which specifies some quantifiable property of an object, and is computed
such that it quantifies some
significant characteristics of the object. We classify the various features
currently employed as
follows:
• General features: Application independent features such as color,
texture, and shape. According to the abstraction level, they can be further
divided into:
- Pixel-level features: Features calculated at each pixel, e.g. color,
location.
- Local features: Features calculated over the results of subdivision of the
image band on image segmentation or edge detection.
- Global features: Features calculated over the entire image or just regular
sub-area of an image.
• Domain-specific features: Application dependent features such as
human faces, fingerprints, and conceptual features.
These features are often a synthesis of low-level features for a specific
domain.
● Feature extraction is done in the following way, image for which the
feature vector is to be
calculated is splited into R, G and B color components and for each of
these three components row and column mean vectors are computed over
which Kekre’s transform is applied to
obtain the coefficients to form the feature vectors (RRK, RCK GRK, GCK
and BRK, BCK for R, G and B planes respectively and a feature database
FDB1 is formed for all
database images
A color histogram H for a given image is defined as a vector H = {h[1],
h[2], . . . h[i], . . . , h[N]} where i represents a color in the color histogram,
h[i] is the number of pixels in color i in that image, and N is the number of
bins in the color histogram, i.e., the number of colors in the adopted color
model. In order to compare images of different sizes, color histograms
should be normalized. The normalized color histogram H is defined for
h[i] ‘= h[i]/XY
●For comparing the similarity of the query image with the database
image we use a parameter called EUCLIDEAN DISTANCE
● Finally to access the retrieval effectiveness and performance of the
technique we use the PRECISION and RECALL as statistical
comparison parameter for our proposed technique of CBIR.
BASIC FORMULAES THAT MAY BE USED:
● Precision=number of relevant images retrieved / total no of images
retrieved
● Recall=no of relevant images retrieved / total no of relevant images in
database
● euclidean distance is given by
●
3.6.1 Reliability
Reliability is the probability that a device will perform its intended function
during a specified period of time under stated conditions.
3.6.2 Availability
the cbir system has high value of availability, as it is the most platform
friendly product.
It is mostly constructed for windows systems.
today these systems are mostly made available on the web for universal
usage.
3.6.4 Maintainability
our product can be maintained in order to:
● correct defects
● meet new requirements
● make future maintenance easier, or
● cope with a changed environment
● also maintainance of large image database is required so that
they can be retrieved fastly and easily
5. Document Approvals
6. Supporting Information