Académique Documents
Professionnel Documents
Culture Documents
Neurocomputing
journal homepage: www.elsevier.com/locate/neucom
art ic l e i nf o a b s t r a c t
Article history: With the bursting development of machine learning and articial intelligence, the pattern recognition
Received 9 October 2015 based image processing techniques are growing faster than ever before. In this paper, we conduct the-
Received in revised form oretical analysis on the natural image super-resolution reconstruction algorithm based on compressive
16 December 2015
perception theory and deep learning model. The image restoration is the purpose of the degraded image
Accepted 16 December 2015
Available online 1 June 2016
processing which make its recovery as it had been before the degradation of ideal image. According to
the views of Fourier optics, optical imaging system is a low pass lter, due to the general inuence of
Keywords: optical diffraction. The deep neural network with hierarchical unsupervised training method stratied
Image super-resolution greed training beforehand matter will be the result of the training as the novel learning supervision
Compressive perception and sensing
probability model of the initial value to make good use of the optical imaging system. The adopted
Deep learning model
compressed sensing theory points out that as long as signal is compressible or sparse, so, if there is a
Neural network structure
Optimization transformation matrix is not related observation matrix on signal can directly obtain compressed form of
Natural images the original signal. Our research adopts the advances of the mentioned technique, in the training step, we
Image restoration use deep neural network to automatically capture the features and in the reconstruction procedure we
use the compressive sensing and dictionary learning theory to reconstruct the high resolution image. By
enhancing both of the steps, our experimental result indicates the feasibility of the novel algorithm. The
prospect is also discussed in the nal part.
& 2016 Elsevier B.V. All rights reserved.
http://dx.doi.org/10.1016/j.neucom.2015.12.125
0925-2312/& 2016 Elsevier B.V. All rights reserved.
118 G. Duan et al. / Neurocomputing 208 (2016) 117126
As the same for the general linear space imaging system, the
available imaging process type is described as the following
expression one.
g x hx f x 1
Where theg xdenotes the phase space and thef xrepresents the
object space. So if we want to recover the cut-off frequency of
information, no matter in theory or practical concept it is impos-
sible. The above conclusion is equivalent to the imaging system as
a Fourier lter which has carried on the limits to solution [22,23].
But in fact there are many methods to estimate, this method does
not have the nature of the Fourier lter by using the method that
can be successfully implemented cut-off frequency information
Fig. 2. The interactive projection for obtaining the solution.
recovery which is expressed below [24].
(
F u Gu=H u following solution [2931].
2
Gu H u UF u " #2
XP X
N X
M qM X
X qN
b
F f g i; j b
Rk i; j; m; nf m; n f
Analytic function is nature of a well-known, if in nite interval
k1j1i1 m1n1
is known, it will be known everywhere. This means that if the two
6
analytic functions on any given interval are identical, they must be
completely consistent on the whole and is the same function. For fringe area, due to its variance is larger and the human
According to the given analytical function on a range of values to visual masking effect, make the human eye is not sensitive to
the function of the overall reconstruction is called analytical con- parasitic corrugated the image edge area, negligible parasitic rip-
ple effect on the edge and at area due to its own variance is small
tinuation [25,26]. For incoherent imaging, the actual image should
and the human parasitic ripple of the area is most sensitive to the
have the following constraints and properties: the negative and
increase of the variance can be thought of purely caused by
boundedness shown as the follows.
( parasitic corrugated. Therefore, when the image get restoration,
f x 4 0; x A X the edge area of parasitic interference is relatively small with the
3 condence the recovery results. In the gure two, we show the
f x 0; x2=X
interactive projection for obtaining the solution [32].
With the noise condition, the imaging process type is described as Fig. 2 illustrates the interactive projection for obtaining the
the follows. solution.
g x hx f x nx 4
As a result of the existence of noise, image super-resolution 3. The proposed image super-resolution algorithm
reconstruction is an ill-posed problem, and we must introduce the
corresponding constraints during recovery. First of all, according to 3.1. The deep learning model
the observation image type looking for a clear image as the
transcendental characteristics, make its have the maximum simi- Every time faced with a large number of the human perception
larity with the super resolution image gray level distribution. data, the brain can easily capture the important information with
Secondly, using the principle of minimum identication informa- low time-consuming. The core problem of articial intelligence is
tion construct a restored image and prior image information items to copy the brain's ability to accurately said information can do
as constraint minimum identications and thus construct a new this effectively. Through the research in recent years, we know
model of the super-resolution restoration, ensure that the restored already had some brain mechanism, which promotes the devel-
image grayscale distribution maximum close to the transcendental opment of articial intelligence. The deep learning as opposed to a
characteristics on the image. The regularization restoration after shallow learning and now a lot of learning methods are shallow
structure algorithm, and they exist some limitations, such as in the
the introduction of constraint model is denoted as formula 5.
case of limited samples of complex function ability is limited, its
X
p generalization ability for complex classication problems under
J b
f g k DH k Ek b
f 2 b
f 5
certain constraints. Deep architecture and the deep learning by
k1
learning a kind of nonlinear network structure and the complex
To solve the model, it involves the general large matrix calcu- function approximation to achieve the characterization of the
lation and the calculation workload is amazing [27,28]. In general, input data distributed said, and in the case of sample set is seldom
fuzzy drop point spread function and under-sampling function is study the nature of the data set. Although shallow learning
far less than the size of the image size. Therefore, we use the application is very extensive, it only effective for simple calculation
120 G. Duan et al. / Neurocomputing 208 (2016) 117126
and can't reach the effect of the reaction of the human brain,
which requires the depth of machine learning. All of these show
that shallow learning network has signicant limitations which
inspired us to depth of network modeling research. Convolutional
neural network was the rst real successfully sample that uses the
multi-layer hierarchical structure has the robustness of the net-
work of deep learning approach, through research, the correlation
of data on the space to reduce number of training parameters. At
present, in eld of image recognition, convolutional neural net-
work has become an effective identication method [3336].
Generally, the basic layers of neural networks are for the fea-
ture extraction, each neuron in the input and the previous layer of
local receptive eld is linked together, and extracts the local
characteristics, according to local characteristics to determine the
location of the relationship between it and other feature space. To
analyze the structure of the deep neural network model, we rstly
show the energy and propagation functions as the follows [37].
X
p v; 1 h
exp E v; h; =Z 7
Fig. 3. The proposed deep neural network structure for super-resolution.
p v; h; 2 exp E v; h; =Z 8 shown as the follows [3841].
XI XJ
1XI 2 XJ
X
I X
J X
I X
J p v; h; 4 wij vi hj vi bj aj h j 10
p v; h; 3 wij vi hj bi vi aj hj 9 i1j1
2i1 j1
i1j1 i1 j1
It has the deep structure of the neural networks tend to have
The traditional algorithm is widely used in the classic network very strong characteristics of the abstract expression ability, rather
structure, but for deep learning training has met with many dif- than shallow structure or the traditional features better char-
culties: rst, the BP algorithm is supervised learning, training acterization of unknown images, but the problem of deep struc-
need a label sample set, but it can get the data are no labels; ture is training hard which need a lot of labeled training samples,
Second, the BP algorithm in the learning structures of many hid- and gradient diffusion problem. This learning method can be
den layer, the learning process slower; Third, the improper para- understood as before the traditional BP algorithm study adopts the
meter choice will lead to local optimal solution. Therefore, to solve method of unsupervised training beforehand. Through preliminary
it, we use the following steps to generally initialize the parameters training, it can be more complicated for subsequent learning
for the neural network system. provides a good initial weight which makes all the right value of
vector is good for global training area. In the gure three, we use
Fig. 3 to show the proposed deep neural network structure for the
later analysis.
transform matrix which is denoted as the follows. precision of refactoring and the high frequency part due to less
X S 11 weight. Reconstruction error is relatively large. But due to the
inuence to the quality of the images in the low frequency com-
At this time, observations of how many only decided by the ponent is given priority to, so to build the image of the overall
structure of the signal, without being limited by the Nyquist fre- quality is better. To modify the prior approaches we conduct
quency, so compression perception is very suitable for use in the optimization in the following procedures [44,45]. Fig. 4 shows the
larger bandwidth of the signal sampling. Therefore, it could be optimization process of the traditional compressive sensing
denoted as: algorithm.
In the code, it will be the same size of the image that is divided
Y X 12
into macro block, using the same random matrix respectively on
In the process of compression perception, the observation
the macro block measurement and at the decoding end, to
matrix plays an important role, and the matrix is suitable to
reconstruct the rst each macro block and then these macros can
determine whether the X in the general process of observation
merge into a whole image. This kind of image reconstruction
information is destroyed it directly relates to whether signal can
model of random measurement matrix storage capacity is small
be accurately reconstructed features. The restriction condition for
with simple structure, and the measurement method based on
the representation is shown below.
block is very suitable for real-time systems. When space related or
1 K v22 r t v22 r 1 K v22 13 coherent source, subspace algorithm performance fell sharply
when the failure. However in the practical application, due to the
In traditional perception algorithm, the observation matrix of
multipath effect, the signal phenomena often exist. The empty
each image block with the same features, such as department with
asked smoothing pretreatment which can to certain extent, solve
Gaussian random matrix. According to characteristics of the visual
the problem of the estimation of coherent sources, but the
system, the human eye for the low frequency components in
image data with greater sensitivity. The quality of reconstructed operation is limited to a specic geometric conguration, such as
image quality and low frequency component of the reconstruction uniform linear array at the same time can also lead to loss of array
error is directly related to the size. In order to improve the quality aperture effectively and the rise of computational complexity.
of the reconstructed image, some can use similar to the JPEG
quantization matrix of the various elements of the observation 3.3. The modied image super-resolution algorithm
matrix different weighted as new observation matrix, so that we
can get a better effect of image restoration. The method of parti- Total compressive and network structured model is bounded
cipating in the low position the elements of the observation the variation function space theory of typical application in the
matrix of data operation, larger weighted and to the participation eld of the image noise removal, etc. It's not smooth constraints
in the high frequency location data computation of matrix ele- imposed by the solution which can remain in image edge infor-
ment, the weighted value is smaller. Because of the reconstruction mation. However, many super-resolution reconstruction practice
in the low frequency part of the picture, when weight is much shows that this approach to the distinction between the edge
bigger, so the low frequency part of the image data has higher region and plain region ability insufcient, especially in low
resolution image sequence is affected by the strong noise [4651]. stronger. To optimize the reconstruction result, we should follow
The common characteristic of the variational method is to use the the next restriction condition and optimization issues [5557].
simple mathematical expressions to distinguish between the (
min 0
images features in different areas. The Fig. 5 shows the overall 16
s:t:Dl a y22 r
process.
However, due to nature image composition is very complicated,
Due to the strong correlation between image pixels, gradient in
such as images of edge and gray scale changes in the both the gray
most areas of the image is close to zero, so the image of gradient is
level jump at areas, there is also a complex texture and the
the sparse space. Minimize applied to image reconstruction which
existence of various noise. So this kind of method is still not fully
can better keep the image edges, consider joining to the total
describes the complex and changeable content in natural images.
variation regularization method, and the vectorization, based on
This model combines with the advantages of both sides, in process
the study of a full variational super-resolution restoration model
of image super resolution reconstruction, we can not only inhibit
denoted as the follows.
the reconstruction process of all kinds of noise, and can reduce
the inuence on the at area and texture structure and the pur- X
vv
min Dl a y22 a1 T i x2 17
pose of making super-resolution reconstruction method has
i1
better performance as well [52,53]. The next formula describes
the model [54]. Set about the terminating condition, this article adopts method
of commonly used, namely when the iteration times meet pre-set
X X 1 2 2 2
3 2 4 2 1=2
J f f i;j f i;j 1 wi;j f i;j f i;j value or restored image between residual meet terminated when
i j setting the threshold value of iteration [58]. In order to get the
14 recovery image with better effect through the method of the
restored image, this paper uses the nonlocal average algorithm
Identication of fuzzy set theory is the analysis, judgment,
and iterative back projection algorithm to get the high resolution
fuzzy phenomenon of a kind of effective tool. Due to the uncer-
image of further processing and the next section will illustrate the
tainty of image information is usually are the fuzzy and not ran-
experimental result.
dom, fuzzy set theory to identify different features in the image
area has a good effect. To use the compressive sensing theory, the
following formula describes transformation matrix.
2 3 4. The experimental simulation
u f 11 u f 12 u f 1N
6 7
6 u f 21 u f 22 u f 2N 7 In this section, we simulate our proposed algorithm compared
6
F Compress 6 7 15
7 with other state-of-the-art methodologies. First, interpolation
4
5
u f M1 u f M2 u f MN algorithm are used to get the initial high resolution image; Sec-
ondly using adaptive adjusting the weight of shock ltering image
According to the Nyquist sampling signal detection, under the gradient, reduce the edge of the image spread, through the for-
condition of compressed sampling is deduced under the condition ward diffusion process to eliminate noise. Before the nal impact
of signal detection. It does not consider the effect of rake merger will lter and diffusion to effectively combine resulting high
and this article will rake the combined signal compression test, resolution image. The experimental results, compared with the
due to the compression related to enhance the signal-to-noise image super-resolution method based on the general interpola-
ratio of core received signal, so its anti-disturbance ability is tion, impact traditional ltering model and the other several
G. Duan et al. / Neurocomputing 208 (2016) 117126 123
Fig. 7. The simulation of the algorithms on the gray scale natural images.
problem, using deep learning good parallelism and the char- [16] Julien Caron, Clment Fallet, Jean-Yves Tinevez, Lionel Moisan, L.
acteristics of global optimization using genetic algorithm and Philippe Braitbart, Gabriel Y. Sirat, Spencer L. Shorte, Conical diffraction illu-
mination opens the way for low phototoxicity super-resolution imaging, Cell
gradient descent of hybrid genetic algorithm combining the ori- Adhes. Migr. 8 (5) (2014) 430439.
ginal high resolution images of the optimal estimation, the [17] Natalia H. Revelo, Dirk Kamin, Sven Truckenbrodt, Aaron B. Wong,
experiment got the signal-to-noise ratio is better than that of Kirsten Reuter-Jessen, Ellen Reisinger, Tobias Moser, Silvio O. Rizzoli, A new
probe for super-resolution imaging of membranes elucidates trafcking
super resolution results of conjugate gradient method. Deep pathways, J. Cell Biol. 205 (4) (2014) 591606.
learning is a focus research eld in recent years which plays an [18] Chujian Bi, Qiushi Zhang, Rui Bao, and Haoxiang Wang, SAR image restoration
important role in machine learning by establishing, simulation, and change detection based on game theory, in: Proceedings of the 2014
International Conference on Intelligent Computing and Internet of Things
hierarchical structure of the brain to realize the external input data (ICIT), IEEE, 2015, pp. 5558.
from low level to high level feature extraction which can explain [19] Uwe Schmidt, Jeremy Jancsary, Sebastian Nowozin, Stefan Roth, and Carsten
external data. Therefore, the combination of deep structure and Rother. Cascades of Regression Tree Fields for Image Restoration, 2014, arXiv
preprint arXiv:1404.2086.
super resolution analysis will obtain better performance. Our [20] Y. Yan, E. Ricci, R. Subramanian, O. Lanz, N. Sebe, No matter where you are:
experimental result proves the robustness and feasibility of the exible graph-guided multi-task learning for multi-view head pose classi-
proposed algorithm. In the future, we will enhance the current cation under target motion, in: IEEE International Conference on Computer
Vision, 2013.
method through the more analysis on the network structure [21] Jiwen Lu, Gang Wang, Pierre Moulin, Human identity and gender recognition
enhancement. from gait sequences with arbitrary walking directions, IEEE Trans. Inf. For-
ensics Secur. 9 (n1) (2014) 4151.
[22] Ernie Esser, Xiaoqun Zhang, Nonlocal patch-based image inpainting through
minimization of a sparsity promoting nonconvex functional, Dept. Math., Univ.
Acknowledgements California Irvine, Irvine, CA, USA, Tech, Rep, 2014.
[23] W.K. Chooi, S. Matthews, M.J. Bull, S.K. Morcos, Multislice helical CT: the value
of multiplanar image reconstruction in assessment of the bronchi and small
This research is supported by the project of Xi'an Science and airways disease, Br. J. Radiol. (2014).
Technology fund: Technology Research of Urban Intelligent [24] Emil Y. Sidky, Rick Chartrand, John M. Boone, Xiaochuan Pan, Constrained
Transportation System Based on big data (No. cxy1509(14)) and minimization for enhanced exploitation of gradient sparsity: application to CT
image reconstruction, Transl. Eng. Health Med., IEEE J. 2 (2014) 118.
the project supported by the Natural Science Foundation of the [25] O. Honda, M. Yanagawa, A. Inoue, A. Kikuyama, S. Yoshida, H. Sumikawa,
Shaanxi Province education department: exible recommendation K. Tobino, M. Koyama, N. Tomiyama, Image quality of multiplanar recon-
system based on hybrid strategy research and development (No. struction of pulmonary CT scans using adaptive statistical iterative recon-
struction, Br. J. Radiol. (2014).
14JK1522). [26] Peng , Thomas Page, Guojie Luo, Wentai Zhang, Pei Wang, Peng Zhang, Peter
Maass, Ming Jiang, Jason Cong, FPGA Acceleration for Simultaneous Medical
Image Reconstruction and Segmentation, in: Proceedings of the 2014 IEEE
22nd Annual International Symposium on Field-Programmable Custom
References Computing Machines (FCCM), IEEE, 2014, pp. 172172.
[27] Ding Lu, Xose Lus Den-Ben, Christian Lutzweiler, Daniel Razansky, Vasilis
[1] Jiwen Lu, Venice Erin Liong, Xiuzhuang Zhou, Jie Zhou, Learning compact Ntziachristos, Image reconstruction in cross-sectional optoacoustic tomo-
binary face descriptor for face recognition, IEEE Trans. Pattern Anal. Mach. graphy based on non-negative constrained model-based inversion, i:n Eur-
Intell. vol. 37 (2015). opean Conferences on Biomedical Optics. International Society for Optics and
[2] Y. Yan, E. Ricci, G. Liu, N. Sebe, Egocentric daily activity recognition via mul- Photonics, 2015, p. 953919.
titask clustering, IEEE Trans. Image Process. 24 (10) (2015) 29842995. [28] Q. Zhao, D. Meng, Z. Xu, W. Zuo, Y. Yan, L1-norm low-rank matrix factorization
[3] Sven Proppert, Steve Wolter, Thorge Holm, Teresa Klein, Sebastian van de by variational bayes, IEEE Trans. Neural Netw. Learn. Syst. 26 (4) (2015)
Linde, Markus Sauer, Cubic B-spline calibration for 3D super-resolution mea- 825839.
surements using astigmatic imaging, Opt. Express 22 (9) (2014) 1030410316. [29] Yulin Xiao, Shangping Zhong, An improved online multiple kernel classica-
[4] Marissa K. Lee, Prabin Rai, Jarrod Williams, Robert J. Twieg, William tion algorithm based on double updating online learning, in: Proceedings of
E. Moerner, Small-molecule labeling of live cell surfaces for three-dimensional the 2014 International Conference on Cloud Computing and Internet of Things
super-resolution microscopy, J. Am. Chem. Soc. 136 (40) (2014) 1400314006. (CCIOT), IEEE, 2014, pp. 109113.
[5] Yongqiang Zhao, Jingxiang Yang, Cheung.-Wai. Chan, Hyperspectral imagery [30] Michael R.H. Hill, Itzhak Fried, Christof Koch, Quantication and classication
super-resolution by spatialspectral joint nonlocal similarity, Sel. Top. Appl. of neuronal responses in kernel-smoothed peristimulus time histograms, J.
Earth Obs. Rem. Sens., IEEE J. 7 (6) (2014) 26712679. Neurophysiol. 113 (4) (2015) 12601274.
[6] Hui Yang, Norman Moullan, Johan Auwerx, Martin A.M. Gijs, Superresolution [31] Haoxiang Wang, Jingbin Wang, An effective image representation method
biological microscopy using virtual imaging by a microsphere nanoscope, using kernel classication, in: Proceedings of the 2014 IEEE 26th International
Small 10 (9) (2014) 17121718. Conference on Tools with Articial Intelligence (ICTAI), IEEE, 2014, p. 853.
[7] Y. Yan, E. Ricci, R. Subramanian, G. Liu, N. Sebe, Multi-task linear discriminant [32] Yudong Zhang, Shuihua Wang, Zhengchao Dong, Classication of Alzheimer
analysis for multi-view action recognition, IEEE Trans. Image Process. 23 (12) disease based on structural magnetic resonance imaging by kernel support
(2014) 55995611. vector machine decision tree, Prog. Electromagn. Res. 144 (2014) 171184.
[8] Xiaoxuan Chen, Chun Qi, Low-rank neighbor embedding for single image [33] Jiwen Lu, Xiuzhuang Zhou, Yap.-Peng. Tan, Yuanyuan Shang, Jie Zhou,
super-resolution, Signal Process. Lett., IEEE 21 (1) (2014) 7982. Neighborhood repulsed metric learning for kinship verication, IEEE Trans.
[9] Jifei Yu, Xinbo Gao, Dacheng Tao, Xuelong Li, Kaibing Zhang, A unied learning Pattern Anal. Mach. Intell. 36 (2) (2014) 331345.
framework for single image super-resolution, Neural Netw. Learn. Syst., IEEE [34] Qi Yuan, Weidong Zhou, Shasha Yuan, Xueli Li, Jiwen Wang, Guijuan Jia, Epi-
Trans. 25 (4) (2014) 780792. leptic EEG classication based on kernel sparse representation, Int. J. neural
[10] Tomer Peleg, Michael Elad, A statistical prediction model based on sparse Syst. 24 (04) (2014) 1450015.
representations for single image super-resolution, Image Process., IEEE Trans. [35] Shenghua Gao, Liang.-Tien. Chia, Wai.-Hung. Tsang, Zhixiang Ren, Concurrent
23 (6) (2014) 25692582. single-label image classication and annotation via efcient multi-layer group
[11] Baraka Jacob Maiseli, Ogada Achieng Elisha, Huijun Gao, A multi-frame super- sparse coding, Multimed., IEEE Trans. 16 (no. 3) (2014) 762771.
resolution method based on the variable-exponent nonlinear diffusion reg- [36] Y. Yan, H. Shen, G. Liu, Z. Ma, C. Gao, N. Sebe, GLocal tells you more: coupling
ularizer, EURASIP J. Image Video Process. 2015 (1) (2015) 116. glocal structural for feature selection with sparsity for image and video clas-
[12] Jiwen Lu, Yap.-Peng. Tan, Gang Wang, Discriminative multimanifold analysis sication, Comput. Vision. Image Underst. volume 124 (7) (2014) 99109.
for face recognition from a single training sample per person, IEEE Trans. [37] Yongqiang Cao, Yang Chen, Deepak Khosla, Spiking deep convolutional neural
Pattern Anal. Mach. Intell. 35 (1) (2013) 3951. networks for energy-efcient object recognition, Int. J. Comput. Vision. 113 (1)
[13] Xiaodong Li, Yun Du, Feng Ling, Super-resolution mapping of forests with (2015) 5466.
bitemporal different spatial resolution images based on the spatial-temporal [38] Hou Le, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, James E. Davis, Joel H. Saltz,
Markov random eld, Sel. Top. Appl. Earth Obs. Remote Sens., IEEE J. 7 (1) Efcient Multiple Instance Convolutional Neural Networks for Gigapixel
(2014). Resolution Image Classication, 2015, arXiv preprint arXiv:1504.07947.
[14] Jing Gao, Ye Wang, Mingjun Cai, Yangang Pan, Haijiao Xu, Junguang Jiang, [39] Caglar Gulcehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio, Learned-
Hongbin Ji, Hongda Wang, Mechanistic insights into EGFR membrane clus- norm pooling for deep feedforward and recurrent neural networks, inL
tering revealed by super-resolution imaging, Nanoscale 7 (6) (2015) Machine Learning and Knowledge Discovery in Databases, Springer Berlin
25112519. Heidelberg (2014), p. 530546.
[15] ShangGuo Hou, Le Liang, Su.Hui Deng, JianFang Chen, Qing Huang, Ya Cheng, [40] Y. Yan, Y. Yang, D. Meng, G. Liu, W. Tong, A. Hauptmann, N. Sebe, Event
ChunHai Fan, Nanoprobes for super-resolution uorescence imaging at the oriented dictionary learning for complex event detection, IEEE Trans. Image
nanoscale, Sci. China Chem. 57 (1) (2014) 100106. Process. 24 (6) (2015) 18671878.
126 G. Duan et al. / Neurocomputing 208 (2016) 117126
[41] Deng Li, Jianshu Chen, Sequence classication using the high-level features [59] Zhangyang Wang, Nasser M. Nasrabadi, Thomas S. Huang, Semisupervised
extracted from deep neural networks, in: Prceedings of the 2014 IEEE Inter- hyperspectral classication using task-driven dictionary learning with Lapla-
national Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, cian regularization, Geosci. Remote Sens., IEEE Trans. 53 (3) (2015) 11611173.
2014. [60] Xixuan Han, Line Clemmensen, Regularized generalized eigen-decomposition
[42] William R. Foland Jr, James H. Martin, Dependency-based semantic role with applications to sparse supervised feature extraction and sparse dis-
labeling using convolutional neural network, in: Proceedings of the Fourth criminant analysis, Pattern Recognit. (2015).
Joint Conference on Lexical and Computational Semantics, 2015, pp. 279288.
[43] Tobias Domhan, Tobias Springenberg, Frank Hutter, Extrapolating learning
curves of deep neural networks, in: ICML 2014 AutoML Workshop, June 2014.
[44] Earnest Ijjina, Paul, C. Krishna Mohan, Human Action Recognition Using
Ganglong Duan received the B.S. and M.S. degrees in
Action Bank Features and Convolutional Neural Networks Computer Vision-
Department of Information Management from Xian
ACCV 2014 Workshops, Springer International Publishing,, 2014. University of Technology, Xian, China, in 2002 and
[45] Yuming Li, Lai-Man Po, Chun-Ho Cheung, Xuyuan Xu, Litong Feng, Fang Yuan,
2005, respectively. He is currently a lecturer with the
Kwok-Wai Cheung, No-Reference Video Quality Assessment with 3D Shearlet Department of Information Management, Xian Uni-
Transform and Convolutional Neural Networks, 2015. versity of Technology, Xian, China. Currently, he is
[46] Dong Wang, Jing Yang, Jiankang Deng, Qingshan Liu, Hierarchical convolu- working towards his Ph.D. degree in School of Eco-
tional neural network for face detection, in: Image and Graphics, Springer nomics and Management at Xian University of Tech-
International Publishing (2015), p. 373384. nology, Xian, China. His current research interests
[47] Jiwen Lu, Yap.-Peng. Tan, Cost-sensitive subspace analysis and extensions for include intelligence information processing and digital
face recognition, IEEE Trans. Inf. Forensics Secur. 8 (3) (2013) 510519. image processing.
[48] Soren Goyal, Paul Benjamin, Object Recognition Using Deep Neural Networks:
A Survey, 2014. arXiv preprint arXiv:1412.3684.
[49] Hongsheng Li, Rui Zhao, Xiaogang Wang. Highly eFcient Forward and Back-
ward Propagation of Convolutional Neural Networks for Pixelwise Classica-
tion, 2014. arXiv preprint arXiv:1412.4526.
[50] Lszl Tth, Combining time-and frequency-domain convolution in convolu- Wenxiu Hu is a Doctor of Management, he is currently
tional neural network-based phone recognition, In: Proceedings of the 2014 the dean of school of Economics and Management,
IEEE International Conference on Acoustics, Speech and Signal Processing Xi'an University of Technology, Xi'an, China. He is also a
(ICASSP), IEEE, 2014, pp. 190194. Professor, a doctoral tutor, the academic leaders of
[51] Toni Hirvonen, Classication of spatial audio location and content using Business Administration. His main research areas
convolutional neural networks, in: Audio Engineering Society Convention, including nancial engineering and risk management,
138, Audio Engineering Society, 2015. corporate mergers and acquisitions, investment man-
[52] Biao Leng, Yu Liu, Kai Yu, Xiangyang Zhang, Zhang Xiong, 3D object under- agement and capital operation.
standing with 3D Convolutional Neural Networks, Inf. Sci. (2015).
[53] Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou, Jun Zhao, Relation classi-
cation via convolutional deep neural network, in: Proceedings of COLING,
2014, pp. 23352344.
[54] Jiwen Lu, Yap.-Peng. Tan, Regularized locality preserving projections and its
extensions for face recognition, IEEE Trans. Syst., Man., Cybern.Part B:
Cybern. 40 (3) (2010) 958963.
[55] Mingsheng Long, Jianmin Wang, Guiguang Ding, Sinno Jialin Pan, Philip S. Yu,
Adaptation regularization: A general framework for transfer learning, Knowl. Jianren Wang is currently an associate professor with
Data Eng., IEEE Trans. 26 (5) (2014) 10761089. the Department of Management Science and Engi-
[56] Ahmad Mozaffari, L. Azad Nasser, Optimally pruned extreme learning machine neering, Xi'an University of Technology, Xi'an, China.
He is the director of the Department of Management
with ensemble of regularization techniques and negative correlation penalty
Science and Engineering at Xi'an University of Tech-
applied to automotive engine coldstart hydrocarbon emission identication,
nology. His current research interests include intelli-
Neurocomputing 131 (2014) 143156.
gence information processing and data mining.
[57] Chujian Bi, Haoxiang Wang, Rui Bao, SAR image change detection using reg-
ularized dictionary learning and fuzzy clustering, in: Proceedings of the 2014
IEEE 3rd International Conference on Cloud Computing and Intelligence Sys-
tems (CCIS), IEEE, 2014, pp. 327330.
[58] Gang Niu, Bo Dai, Makoto Yamada, Masashi Sugiyama, Information-theoretic
semi-supervised metric learning via entropy regularization, Neural Comput.
26 (8) (2014) 17171762.