Chuanbo Chen

Huazhong University of Science and Technology, Wu-han-shih, Hubei, China

Are you Chuanbo Chen?

Claim your profile

Publications (44)8.58 Total impact

  • Journal of Electronic Imaging 05/2015; 24(3):033009. DOI:10.1117/1.JEI.24.3.033009 · 0.85 Impact Factor
  • Xiaobing Pei, Tao Wu, Chuanbo Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel projective nonnegative matrix factorization (PNMF) method for enhancing the clustering performance is presented, called automated graph regularized projective nonnegative matrix factorization (AGPNMF). The idea of AGPNMF is to extend the original PNMF by incorporating the automated graph regularized constraint into the PNMF decomposition. The key advantage of this approach is that AGPNMF simultaneously finds graph weights matrix and dimensionality reduction of data. AGPNMF seeks to extract the data representation space that preserves the local geometry structure. This character makes AGPNMF more intuitive and more powerful than the original method for clustering tasks. The kernel trick is used to extend AGPNMF model related to the input space by some nonlinear map. The proposed method has been applied to the problem of document clustering using the well-known Reuters-21578, TDT2, and SECTOR data sets. Our experimental evaluations show that the proposed method enhances the performance of PNMF for document clustering.
    10/2014; 44(10):1821-1831. DOI:10.1109/TCYB.2013.2296117
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a novel label propagation (LP) method is presented, called the manifold adaptive label propagation (MALP) method, which is to extend original LP by integrating sparse representation constraint into regularization framework of LP method. Similar to most LP, first of all, MALP also finds graph edges from given data and gives weights to the graph edges. Our goal is to find graph weights matrix adaptively. The key advantage of our approach is that MALP simultaneously finds graph weights matrix and predicts the label of unlabeled data. This paper also derives efficient algorithm to solve the proposed problem. Extensions of our MALP in kernel space and robust version are presented. The proposed method has been applied to the problem of semi-supervised face clustering using the well-known ORL, Yale, extended YaleB, and PIE datasets. Our experimental evaluations show the effectiveness of our method.
    09/2014; DOI:10.1109/TCYB.2014.2358592
  • [Show abstract] [Hide abstract]
    ABSTRACT: Based on the fact that human attention is more likely to be attracted by different objects or statistical outliers of a scene, a bottom-up saliency detection model is proposed. Our model regards the saliency patterns of an image as the outliers in a dataset. For an input image, first, each image element is described as a feature vector. The whole image is considered as a dataset and an image element is classified as a saliency pattern if its corresponding feature vector is an outlier among the dataset. Then, a binary label map can be built to indicate the salient and the nonsalient elements in the image. According to the Boolean map theory, we compute multiple binary maps as a set of Boolean maps which indicate the outliers in multilevels. Finally, we linearly fused them into the final saliency map. This saliency model is used to predict the human eye fixation, and has been tested on the most widely used three benchmark datasets and compared with eight state-of-the-art saliency models. In our experiments, we adopt the shuffled the area under curve metric to evaluate the accuracy of our model. The experimental results show that our model outperforms the state-of-the-art models on all three datasets. (C) 2014 SPIE and IS&T
    Journal of Electronic Imaging 09/2014; 23(5). DOI:10.1117/1.JEI.23.5.053023 · 0.85 Impact Factor
  • 09/2014; 9(9). DOI:10.4304/jcp.9.9.2167-2172
  • Computers & Electrical Engineering 08/2014; DOI:10.1016/j.compeleceng.2014.07.011 · 0.99 Impact Factor
  • The Visual Computer 01/2014; DOI:10.1007/s00371-014-1007-5 · 1.07 Impact Factor
  • Chuanbo Chen, Guangwei Wang, Mudar Sarem
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a non-symmetry and anti-packing image representation model (NAM) has been proposed. NAM is a hierarchical image representation method and it aims to provide faster operations and less storage requirement. By taking a rectangle sub-pattern, for example, we describe the idea of NAM and its encoding algorithm.In addition, an approach for adaptive area histogram equalization for image contrast enhancement based on a NAM image is presented. The contrast enhancement approach is designed to meet the NAM image representation and it can be duplicated with faster operation. The complexity analysis and the experimental results show that the NAM based algorithm for image contrast enhancement is faster and more effective than that based on matrix image.
    Computers & Electrical Engineering 09/2011; 37:669-680. DOI:10.1016/j.compeleceng.2011.07.006 · 0.99 Impact Factor
  • Guangwei Wang, Chuanbo Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a non-symmetry and anti-packing image representation model (NAM). NAM is a hierarchical image representation method and its aim is less data amount and faster operation. By taking a rectangle sub-pattern for example, we describe the idea of NAM. In addition, an approach for adaptive area histogram equalization image contrast enhancement based on a NAM image is presented. The contrast enhancement approach is designed to meet the NAM image representation and can be fast implemented. In this work, the contrast enhancement method combines dynamic range modification and adaptive area histogram equalization to improve the visualization of images. Complexity analysis and experimental results show that the NAM based algorithm for image contrast enhancement is faster and more effective than that based on matrix image.
    Image and Signal Processing (CISP), 2010 3rd International Congress on; 11/2010
  • Pengyi Gao, Chuanbo Chen, Sheng Qin, Yingsong Hu
    [Show abstract] [Hide abstract]
    ABSTRACT: Although many global optimization search algorithms may be used to train feedforward neural networks, these algorithms have some weaknesses such as dependence of initial solution. This paper proposes a novel hybrid global optimization method for classification problem, called GTA, which combines the advantages of Genetic algorithm and Tabu search. The training process in proposed method is divided into two phase. First, a promising initial solution is searched by GA algorithm, and next the best solution is selected by tabu search. In this work, the optimization method and test are discussed. Results obtained by testing Diabetes Data Set have shown that the approach performs better than other optimization algorithm.
    Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on; 03/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this work, a hybrid neural network model (HNNM) is proposed, which combines the advantages of genetic algorithm, multi-agents and reinforcement learning. In order to generate networks with few connections and high classification performance, HNNM could dynamically prune or add hidden neurons at different stages of the training process. Experimental results have shown to be better than those obtained by the most commonly used optimization techniques.
    Advances in Neural Networks - ISNN 2010, 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part I; 01/2010
  • Pengyi Gao, Chuanbo Chen, Sheng Qin
    [Show abstract] [Hide abstract]
    ABSTRACT: The selection for the number of hidden nodes for a neural network is of critical importance. This paper proposes a novel algorithm to determine the number of hidden nodes of a neural network and optimize it. In the method, the number of hidden nodes H is first computed by empirical formulas, and the range of H is determined according to computed result. Then, the "three points search" is applied to search the best number of hidden nodes within the range. Finally, a GTA(Genetic algorithm and Tabu search Algorithm Approach) is developed to train the weights of neural network constructed with the best H. Test results obtained by using Iris data set has shown to be efficient, and better than those by the most commonly used optimization techniques.
  • Guangwei Wang, Chuanbo Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a non-symmetry and anti-packing object pattern representation model (NAM) for object detection. A set of distinctive sub-patterns (object parts) is constructed from a set of sample images of the object class; object pattern are then represented using sub-patterns, together with spatial relations observed among the sub-patterns. Many feature descriptors can be used to describe these sub-patterns.The NAM model codes the global geometry of object category, and the local feature descriptor of sub-patterns deal with the local variation of object. By using Edge Direction Histogram (EDH) features to describe local sub-pattern contour shape within an image, we found that richer shape information is helpful in improving recognition performance. Based on this representation, several learning classifiers are used to detect instances of the object class in a new image. The experimental results on a variety of categories demonstrate that our approach provides successful detection of the object within the image.
  • Guangwei Wang, Chuanbo Chen, Kang Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a non-symmetry and anti-packing image representation model (NAM). NAM is a hierarchical image representation method and its aim is less data amount and faster operation. By taking a rectangle sub-pattern for example, we describe the idea of NAM. In this work, based on block-wise LS linear predictor method, a gray-coded bit-plane binary image NAM representation method is presented to compress the error image. The compression performance has been further improved. Experimental results show that our compression scheme is clearly better from data compression point of view than other methods.
    Network Infrastructure and Digital Content, 2010 2nd IEEE International Conference on; 01/2010
  • Xiaobing Pei, ShaoHong Fang, ChuanBo Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: Non-negative matrix factorization (NMF) is useful in finding basis information of non-negative data. It is a new dimension reduction method. In this paper, a Group Locality Preserving Orthogonal Nonnegative Matrix Factorization (GLPONMF) is investigated. The idea is to extend the NMF method in order to extract basis vectors for each sample class and at the same time enforce the locality preserving orthogonal properties. Finally, the experimental evaluation has been given.
    Seventh International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2010, 10-12 August 2010, Yantai, Shandong, China; 01/2010
  • Source
    Yunping Zheng, Chuanbo Chen, Sarem Mudar
    [Show abstract] [Hide abstract]
    ABSTRACT: A representation method using the non-symmetry and anti-packing model (NAM) for data compression of binary images is presented. The NAM representation algorithm is compared with the popular linear quadtree and run length encoding algorithms. Theoretical and experimental results show that the algorithm has a higher compression ratio for both lossy and lossless cases of binary images and better reconstructed quality for the lossy case.
    Tsinghua Science & Technology 02/2009; 14(1):139-145. DOI:10.1016/S1007-0214(09)70020-3
  • Wei Huang, Chuanbo Chen, Mudar Sarem
    [Show abstract] [Hide abstract]
    ABSTRACT: Although the quadtree has many merits in image representation and image processing, its compactness is impaired by the excessive emphasis on the symmetry of segmentations. In this paper, a lossless gray level image representation, titled overlapped rectangle image representation (ORIR), is presented. The ORIR has removed the constraint of the symmetric segmentations and is capable of coding some detached pixels by using a single rectangle. These characteristics have made the ORIR a highly compact representation. The theoretical analyses and the experimental results in this paper show that the ORIR is greatly superior to the linear quadtree in the aspect of the memory efficiency.
    Knowledge Acquisition and Modeling Workshop, 2008. KAM Workshop 2008. IEEE International Symposium on; 01/2009
  • Shaohong Fang, Chuanbo Chen, Yunping Zheng
    [Show abstract] [Hide abstract]
    ABSTRACT: Image representation is an important issue in computer graphics, computer vision, robotics, image processing and pattern recognition. In this paper, we proposed an improved color image representation method by using the direct non-symmetry and anti-packing model with triangles and rectangles (DNAMTR). Also, we propose an algorithm of the DNAMTR for color images and analyze the total data amount of the algorithm. By comparing the representation algorithm of the DNAMTR with those of the latest direct non-symmetry and anti-packing model (DNAM) and the popular linear quadtree, the experimental results presented in this paper show that the former can greatly reduce the numbers of subpatterns or nodes and simultaneously save the data storage much more effectively than the latter.
    First IITA International Joint Conference on Artificial Intelligence, Hainan Island, China, 25-26 April 2009; 01/2009
  • Mudar Sarem, Yunping Zheng, Chuanbo Chen
    [Show abstract] [Hide abstract]
    ABSTRACT: With the rapid development of mobile communication systems, demands for the transmission of multimedia information are increasing day by day. The effective transmission of images can be increased by getting smaller image file that is obtained by compression. However, image quality is often sacrificed in the compression process. Therefore, there is a need to represent images with less data storage without sacrificing the image quality. In this paper, inspired by the concept of the packing problem, we present a new Non-symmetry and Anti-packing Model with Rectangles (NAMR) for lossy and lossless image representation in order to represent the pattern more effectively and flexiblely. Also, in this paper, we propose an algorithm of NAMR and analyze the data amount of this algorithm. The theoretical analyses and experimental results presented in this paper show that when the representation method of NAMR is compared with that of the popular linear quadtree, not only can the former reduce the data storage much more effectively than the latter in lossless case, but also the former has a better reconstruction quality than the latter in lossy case.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a new Non-symmetry and Anti-packing Model (NAM) representation method for gray image. By describing the NAM and Gray-Coded Bit-Plane Decomposition (GC-BPD), a novel NAM-based representation algorithm for gray image is presented. The theoretical analyses and experimental results show that the NAM-based representation method can reduce the data storage much more effectively than the linear quadtree-based representation method and is a better method to represent the gray image. The method is a new research area and it is valuable for the theoretical research and potential practical values such as decreasing the storage room, quickening the process procedure, matching pattern, and so on.