Search For:

Displaying 1-14 out of 14 total
Robust Image Denoising Using Kernel-Induced Measures
Found in: Pattern Recognition, International Conference on
By Keren Tan, Songcan Chen, Daoqiang Zhang
Issue Date:August 2004
pp. 685-688
In this paper, we propose a class of novel nonlinear robust filters for image denoising by incorporating kernel -induced measures into classical linear mean filter. Particularly, we place more focus on Gaussian kernel based filter (GK) due to its simplicit...
 
Double Guarantee for Security Localization in Wireless Sensor Network
Found in: Wireless and Mobile Communications, International Conference on
By Jingjing Gu, Songcan Chen, Yi Zhuang
Issue Date:August 2009
pp. 99-104
Wireless Sensor Network security localization technologies are usually designed just for one type of attack or single step transmission for the message packets, which would be less robust in complex network environment. In this paper, we propose a novel WS...
 
Enhanced Pictorial Structures for precise eye localization under incontrolled conditions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiaoyang Tan, Fengyi Song, Zhi-Hua Zhou, Songcan Chen
Issue Date:June 2009
pp. 1621-1628
In this paper, we present an enhanced pictorial structure (PS) model for precise eye localization, a fundamental problem involved in many face processing tasks. PS is a computationally efficient framework for part-based object modelling. For face images ta...
 
Matrix-Pattern-Oriented Ho-Kashyap Classifier with Early Stopping
Found in: Computer Science and Information Engineering, World Congress on
By Zhe Wang, Songcan Chen, Zhisong Pan, Xuelei Ni
Issue Date:April 2009
pp. 689-693
Matrix-pattern-oriented Ho-Kashyap classifier has been demonstrated to have a superior classification performance to its vector classifier. However, it is found that the matrixized classifier takes a large computational complexity for convergence in some c...
 
Discriminative Canonical Correlation Analysis with Missing Samples
Found in: Computer Science and Information Engineering, World Congress on
By Tingkai Sun, Songcan Chen, Jingyu Yang, Xuelei Hu, Pengfei Shi
Issue Date:April 2009
pp. 95-99
Multimodal recognition emerges when the non-robustness of unimodal recognition is noticed in real applications. Canonical correlation analysis (CCA) is a powerful tool of feature fusion for multimodal recognition. However, in CCA, the samples must be pairw...
 
A Novel Method of Combined Feature Extraction for Recognition
Found in: Data Mining, IEEE International Conference on
By Tingkai Sun, Songcan Chen, Jingyu Yang, Pengfei Shi
Issue Date:December 2008
pp. 1043-1048
Multimodal recognition is an emerging technique to overcome the non-robustness of the unimodal recognition in real applications. Canonical correlation analysis (CCA) has been employed as a powerful tool for feature fusion in the realization of such multimo...
 
MC: An Unsupervised Data Preprocessing for Classification
Found in: Intelligent Information Technology Applications, 2007 Workshop on
By Enliang Hu, Songcan Chen, Xuesong Yin
Issue Date:December 2008
pp. 259-263
The generalization ability of a classifier is often inherently associated with both the intra-class compactness and the inter-class separability. Owing to the fact that some current lower-dimensional manifold embedding techniques as a preprocessing for cla...
 
An Improvement of BAM in Storage Capacity and Error-Correction Capability
Found in: Data, Privacy, and E-Commerce, International Symposium on
By Min Wang, Songcan Chen
Issue Date:November 2007
pp. 164-166
With the introduction of combination into the Quick Learning for Bidirectional Associative Memory (QLBAM), a Combined BAM (CBAM) is presented. The new model aims to improve the storage capacity and error-correction capability without destroying the compone...
 
MultiK-MHKS: A Novel Multiple Kernel Learning Algorithm
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Zhe Wang, Songcan Chen, Tingkai Sun
Issue Date:February 2008
pp. 348-353
With the newly-proposed Canonical Correlation Analysis (CCA) named NmCCA that is an alternative formulation of CCA for more than two views of the same phenomenon, we develop a new effective multiple kernel learning algorithm. First, we adopt the empirical ...
 
Exponential Bidirectional Associative Memory Based on Small-world Architecture
Found in: International Conference on Natural Computation
By Min Wang, Songcan Chen
Issue Date:August 2007
pp. 391-397
Most of neural associative memory models have fully-connected structure. However, from both the neurobiological viewpoint and the hardware implementation perspective, it seems more reasonable to consider such networks with both predominantly local connecti...
 
A Novel Approach of Rough Set-Based Attribute Reduction Using Fuzzy Discernibility Matrix
Found in: Fuzzy Systems and Knowledge Discovery, Fourth International Conference on
By Ming Yang, Songcan Chen, Xubing Yang
Issue Date:August 2007
pp. 96-101
Rough set approach is one of effective attribute reduction (also called a feature selection) methods that can preserve the meaning of the attributes(features). However, most of existing algorithms mainly aim at information systems or decision tables with d...
 
Adaptive Kernel Principal Component Analysis with Unsupervised Learning of Kernels
Found in: Data Mining, IEEE International Conference on
By Daoqiang Zhang, Zhi-Hua Zhou, Songcan Chen
Issue Date:December 2006
pp. 1178-1182
Choosing an appropriate kernel is one of the key problems in kernel-based methods. Most existing kernel selection methods require that the class labels of the training examples are known. In this paper, we propose an adaptive kernel selection method for ke...
 
Learning Non-Metric Partial Similarity Based on Maximal Margin Criterion
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiaoyang Tan, Songcan Chen, Jun Li, Zhi-Hua Zhou
Issue Date:June 2006
pp. 138-145
The performance of many computer vision and machine learning algorithms critically depends on the quality of the similarity measure defined over the feature space. Previous works usually utilize metric distances which are ofen epistemologically different f...
 
Heterogeneous cross domain ranking in latent space
Found in: Proceeding of the 18th ACM conference on Information and knowledge management (CIKM '09)
By Bo Wang, Jie Tang, Songcan Chen, Wei Fan, Yanzhu Liu, Zi Yang
Issue Date:November 2009
pp. 987-996
Traditional ranking mainly focuses on one type of data source, and effective modeling still relies on a sufficiently large number of labeled or supervised examples. However, in many real-world applications, in particular with the rapid growth of the Web 2....
     
 1