Key Laboratory of Image Processing

Wuhan, China

Key Laboratory of Image Processing

Wuhan, China
SEARCH FILTERS
Time filter
Source Type

Wu A.,Huazhong University of Science and Technology | Wu A.,Key Laboratory of Image Processing | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing | Zhang J.,East China Jiaotong University
Neurocomputing | Year: 2012

In this paper, the global exponential convergence of a general class of periodic neural networks with time-varying delays is investigated. Based on the theory of mixed monotone operator, a testable algebraic criteria for ascertaining global exponential convergence is derived. Furthermore, the rate of exponential convergence and bound of the networks are also estimated. Finally, a numerical example is given to show the effectiveness of the obtained results. © 2011.


Wu A.,Hubei Normal University | Wu A.,Xi'an Jiaotong University | Wu A.,Huazhong University of Science and Technology | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing
Circuits, Systems, and Signal Processing | Year: 2014

Memristive neural systems are a ground breaking concept that is helping us understand the behavior of electronic brain. In this paper, a general class of memristive neural systems with time delays is formulated and investigated. Several succinct criteria are given to ascertain the input-to-state stability via nonsmooth analysis and control theory. These conditions, which can be directly derived from the parameters of the system, are easily verified. The obtained results extend some previous works on conventional neural systems. A numerical example is provided to show the efficiency of the proposed approach. © 2013 Springer Science+Business Media New York.


Wen S.,Huazhong University of Science and Technology | Wen S.,Key Laboratory of Image Processing | Huang T.,Texas A&M University at Qatar | Zeng Z.,Huazhong University of Science and Technology | And 3 more authors.
Neural Networks | Year: 2015

This paper addresses the problem of circuit design and global exponential stabilization of memristive neural networks with time-varying delays and general activation functions. Based on the Lyapunov-Krasovskii functional method and free weighting matrix technique, a delay-dependent criteria for the global exponential stability and stabilization of memristive neural networks are derived in form of linear matrix inequalities (LMIs). Two numerical examples are elaborated to illustrate the characteristics of the results. It is noteworthy that the traditional assumptions on the boundness of the derivative of the time-varying delays are removed. © 2014 Elsevier Ltd.


Wu A.,Huazhong University of Science and Technology | Wu A.,Key Laboratory of Image Processing | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing
Neural Networks | Year: 2012

The paper introduces a general class of memristor-based recurrent neural networks with time-varying delays. Conditions on the nondivergence and global attractivity are established by using local inhibition, respectively. Moreover, exponential convergence of the networks is studied by using local invariant sets. The analysis in the paper employs results from the theory of differential equations with discontinuous right-hand sides as introduced by Filippov. The obtained results extend some previous works on conventional recurrent neural networks. © 2012.


Chen B.,Hubei Normal University | Chen J.,Hubei Normal University | Chen J.,Huazhong University of Science and Technology | Chen J.,Key Laboratory of Image Processing
Neural Networks | Year: 2016

The present paper studies global O(t-α) stability and global asymptotical periodicity for a non-autonomous fractional-order neural networks with time-varying delays (FDNN). Firstly, some sufficient conditions are established to ensure that a non-autonomous FDNN is global O(t-α) stable based on a new Lyapunov function method and Leibniz rule for fractional differentiation. Next it is shown that the periodic or autonomous FDNN cannot generate exactly nonconstant periodic solution under any circumstances. Finally, we show that all solutions converge to a same periodic function for a periodic FDNN by using a fractional-order differential inequality technique. Our issues, methods and results are all new. © 2015 Elsevier Ltd.


Liu X.,Huazhong University of Science and Technology | Liu X.,Key Laboratory of Image Processing | Liu X.,Wuhan University of Science and Technology | Liu X.,Hubei Province Key Laboratory of Intelligent Information Processing | And 2 more authors.
Neurocomputing | Year: 2015

Mass localization is a crucial problem in computer-aided detection (CAD) system for the diagnosis of suspicious regions in mammograms. In this paper, a new automatic mass detection method for breast cancer in mammographic images is proposed. Firstly, suspicious regions are located with an adaptive region growing method, named multiple concentric layers (MCL) approach. Prior knowledge is utilized by tuning parameters with training data set during the MCL step. Then, the initial regions are further refined with narrow band based active contour (NBAC), which can improve the segmentation accuracy of masses. Texture features and geometry features are extracted from the regions of interest (ROI) containing the segmented suspicious regions and the boundaries of the segmentation. The texture features are computed from gray level co-occurrence matrix (GLCM) and completed local binary pattern (CLBP). Finally, the ROIs are classified by means of support vector machine (SVM), with supervision provided by the radiologist's diagnosis. To deal with the imbalance problem regarding the number of non-masses and masses, supersampling and downsampling are incorporated. The method was evaluated on a dataset with 429 craniocaudal (CC) view images, containing 504 masses. Among them, 219 images containing 260 masses are used to optimize the parameters during MCL step, and are used to train SVM. The remaining 210 images (with 244 masses) are used to test the performance. Masses are detected with 82.4% sensitivity with 5.3 false positives per image (FPsI) with MCL, and after active contour refinement, feature analysis and classification, it obtained 1.48 FPsI at the sensitivity 78.2%. Testing on 164 normal mammographic images showed 5.18 FPsI with MCL and 1.51 FPsI after classification. Experiments on mediolateral oblique (MLO) images have also been performed, the proposed method achieved a sensitivity 75.6% at 1.38 FPsI. The method is also analyzed with free response operating characteristic (FROC) and compared with previous methods. Overall, the proposed method is a promising approach to achieve low FPsI while maintaining a high sensitivity. © 2014 Elsevier B.V.


Wang G.,Huazhong University of Science and Technology | Wang G.,Key Laboratory of Image Processing | Yin Q.,Huazhong University of Science and Technology | Yin Q.,Key Laboratory of Image Processing | And 2 more authors.
Neurocomputing | Year: 2013

This paper focuses on the exponential synchronization problem of coupled fuzzy neural networks with disturbances and mixed time-delays. For the network under study, the effects of both random and vague factors are considered. By stochastic analysis techniques, we establish sufficient conditions for the coupled fuzzy neural networks to be exponentially synchronized in the mean square. It is demonstrated that the network synchronizability is largely dependent on the coupling structure of such network. Moreover, the information exchange network needs not to be undirected or strongly connected. Finally, numerical simulations are given to verify the usefulness and effectiveness of our results. © 2012 Elsevier B.V.


Chen J.,Huazhong University of Science and Technology | Chen J.,Key Laboratory of Image Processing | Zeng Z.,Huazhong University of Science and Technology | Zeng Z.,Key Laboratory of Image Processing | And 2 more authors.
Neural Networks | Year: 2014

In this paper, the existence, uniqueness and stability of almost periodic solution for a class of delayed memristor-based neural networks are studied. By using a new Lyapunov function method, the neural network that has a unique almost periodic solution, which is globally exponentially stable is proved. Moreover, the obtained conclusion on the almost periodic solution is applied to prove the existence and stability of periodic solution (or equilibrium point) for delayed memristor-based neural networks with periodic coefficients (or constant coefficients). The obtained results are helpful to design the global exponential stability of almost periodic oscillatory memristor-based neural networks. Three numerical examples and simulations are also given to show the feasibility of our results. © 2014 Elsevier Ltd.


Pan J.,Key Laboratory of Image Processing | Pan J.,Huazhong University of Science and Technology | Pan J.,Hubei Engineering University | Hu H.,Key Laboratory of Image Processing | And 4 more authors.
Entropy | Year: 2016

By exploiting the statistical analysis method, human dynamics provides new insights to the research of human behavior. In this paper, we analyze the characteristics of the computer operating behavior through a modified multiscale entropy algorithm with both the interval time series and the number series of individuals' operating behavior been investigated. We also discuss the activity of individuals' behavior from the three groups denoted as the retiree group, the student group and the worker group based on the nature of their jobs. We find that the operating behavior of the retiree group exhibits more complex dynamics than the other two groups and further present a reasonable explanation for this phenomenon. Our findings offer new insights for the further understanding of individual behavior at different time scales. © 2015 by the authors.


Xia R.,CAS Shenyang Institute of Automation | Xia R.,Chinese Academy of Sciences | Xia R.,Key Laboratory of Image Processing | Zhao J.,CAS Shenyang Institute of Automation | And 9 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2011

This paper presents a simple and computationally efficient saliency extraction method for detecting dim small target from single frame in heterogeneous background. The proposed method is based on background subtraction (BS), which identifies targets from the portion of a image that differs significantly from a background model. A set of horizondirectional filters (HDF) with multi-scales are first implemented to effectively recover the background maps from the input image. As a result, the foreground maps are extracted by computing the absolute difference between the input image and the estimated background maps. Then the foreground maps are fused into the total saliency map using a simple scheme. Finally, the experimental results of various cluttered background images show that the proposed method is efficient and has an outstanding performance in dim small target detection just by thresholding the saliency map. © 2011 SPIE.

Loading Key Laboratory of Image Processing collaborators
Loading Key Laboratory of Image Processing collaborators