By Topic

Pattern Recognition, 2008. CCPR '08. Chinese Conference on

Date 22-24 Oct. 2008

Filter Results

Displaying Results 1 - 25 of 96
  • CCPR 2008 [Title page]

    Publication Year: 2008, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (81 KB)
    Freely Available from IEEE
  • CCPR 2008 [Copyright notice]

    Publication Year: 2008, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (113 KB)
    Freely Available from IEEE
  • CCPR 2008 Sponsorship and Organization

    Publication Year: 2008, Page(s):1 - 2
    Request permission for commercial reuse | PDF file iconPDF (273 KB)
    Freely Available from IEEE
  • CCPR 2008 Forwards

    Publication Year: 2008, Page(s):1 - 2
    Request permission for commercial reuse | PDF file iconPDF (229 KB)
    Freely Available from IEEE
  • CCPR 2008 Keynote Speech 1

    Publication Year: 2008, Page(s): 1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (129 KB) | HTML iconHTML

    Summary form only given. Sensory information acquired by pattern recognition systems is invariably subject to environmental and sensing conditions, which may change over time. For imaging sensors, for instance, this includes illumination changes, pose and view-point changes, noise, distortion, blurring, etc. This has inevitably a significant negative impact on the performance of pattern recognitio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CCPR 2008 Keynote Speech 2

    Publication Year: 2008, Page(s): 1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (126 KB) | HTML iconHTML

    With an increasing amount of audio and video materials made available on the web, information extraction from multimedia documents is becoming a key area of growing business and technology interest. Research opportunities range from traditional topics, such as multimedia signal representation, processing, coding, modeling, authentication, and recognition, to emerging subjects, such as language mod... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CCPR 2008 Keynote Speech 3 and Keynote Speech 4

    Publication Year: 2008, Page(s): 1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (195 KB)

    Firstly, we consider the space of small image patches, say 7times7 pixels, and show that patches cropped from natural images are distributed in a wide variety of manifolds from low dimensional manifolds for regular textons and image primitives, to high dimensional manifolds for textures. Secondly, we introduce a learning and modeling method which pursues these manifolds by information projection, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CCPR 2008 Table of contents

    Publication Year: 2008, Page(s):1 - 8
    Request permission for commercial reuse | PDF file iconPDF (285 KB)
    Freely Available from IEEE
  • CCPR 2008 author index

    Publication Year: 2008, Page(s):1 - 2
    Request permission for commercial reuse | PDF file iconPDF (82 KB)
    Freely Available from IEEE
  • Combining KPCA and PSO for Pattern Denoising

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (635 KB)

    KPCA based pattern denoising has been addressed. This method, based on machine learning, maps nonlinearly patterns in input space into a higher-dimensional feature space by kernel functions, then performs PCA in feature space to realize pattern denoising. The key difficulty for this method is to seek the pre-image or an approximate pre-image in input space corresponding to the pattern after denois... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Domain Adaptation in NLP Based on Hybrid Generative and Discriminative Model

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (230 KB)

    This study investigates the domain adaptation problem for nature language processing tasks in the distributional view. A novel method is proposed for domain adaptation based on the hybrid model which combines the discriminative model with the generative model. The advantage of the discriminative model is to have lower asymptotic error, while the advantage of the generative model can easily incorpo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-Supervised Learning with Gaussian Processes

    Publication Year: 2008, Page(s):1 - 5
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (117 KB) | HTML iconHTML

    As a supervised learning algorithm, the standard Gaussian processes has the excellent performance of classification. In this paper, we present a semi-supervised algorithm to learning a Gaussian process classifier, which incorporating a graph-based construction of semi-supervised kernels in the presence of labeled and unlabeled data, and expanding the standard Gaussian processes algorithm into the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New Concept for Discriminator Design: From Classifier to Discriminator

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (137 KB) | HTML iconHTML

    This paper introduces a new concept of designing a discriminant analysis method (discriminator), which starts from a local mean based nearest neighbor (LM-NN) classifier and uses its decision rule to direct the design of a discriminator. The derived discriminator, called local mean based nearest neighbor discriminator (LM-NND), matches the LM-NN classifier optimally in theory. The proposed LM-NND ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convergence Properties of Particle Filter Algorithm

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (247 KB)

    The basic sampling importance resampling algorithm is the basic for improving particle filter methods which are widely utilized in optimal filtering problems. In our paper, we introduce a modified basic SIR algorithm and analyze the convergence property of the modified basic SIR algorithm. Furthermore, when the recursive time is finite and the forth-order moment of the interesting function w.r.t t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-Supervised Clustering Algorithm for Multi-Density and Complex Shape Dataset

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (215 KB) | HTML iconHTML

    There are many complicated data in real world, clustering analysis should be able to find the clusters of different shapes and densities. The existing typical clustering algorithms do not perform well on multi-density data. A semi-supervised clustering algorithm for multi-density dataset SCMD is proposed. The pairwise constraints: must-link and cannot-link that reflect the distribution of multi-de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Manifold-Based Supervised Feature Extraction and Face Recognition

    Publication Year: 2008, Page(s):1 - 4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (98 KB) | HTML iconHTML

    Unsupervised discriminant projection (UDP) has a good effect on face recognition problem, but it has not made full use of the training samples' class information that is useful for classification. Linear discrimination analysis (LDA) is a classical face recognition method. It is effective for classification, but it can not discover the samples' nonlinear structure. This paper develops a manifold-b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-Class Classification Based on Fisher Criteria with Weighted Distance

    Publication Year: 2008, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (153 KB) | HTML iconHTML

    Linear discriminant analysis (LDA) is an efficient dimensionality reduction algorithm. In this paper we propose a new Fisher criteria with weighted distance (FCWWD) to find an optimal projection for multi-class classification tasks. We replace the classical linear function with a nonlinear weight function to describe the distances between samples in Fisher criteria. What's more, we give a new algo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Informative Component Extraction with Robustness Consideration

    Publication Year: 2008, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (174 KB) | HTML iconHTML

    Small sample size of training data might bring trouble as the bias of the estimated parameters for a pattern recognition system. Plug-in test statistics suffer from large estimation errors, often causing the performance to degrade as the measurement vector dimension increases. The informative component extraction method helps to solve this problem by throwing out some dimensions which have relativ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Novel Feature Extraction Method and Its Relationships with PCA and KPCA

    Publication Year: 2008, Page(s):1 - 6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (256 KB)

    A new feature extraction method for high dimensional data using least squares support vector regression (LSSVR) is presented. Firstly, the expressions of optimal projection vectors are derived into the same form as that in the LSSVR algorithm by specially extending the feature of training samples. So the optimal projection vectors could be obtained by LSSVR. Then, using the kernel tricks, the data... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conditional Bayesian Network Mix Classifiers using on Performance -Appraising of Enterprise

    Publication Year: 2008, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (223 KB)

    At present, some deficiencies exist in the methods using to appraising enterprise performance. And there are the problems of efficiency and reliability in learning conditional Bayesian network. In this paper, a conditional Bayesian network structure is established by using sorting nodes and local search & scoring. And a conditional Bayesian network is combined with a naive Bayes classifier to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstruction Strategy for Multi-Class SVM Based on Posterior Probability

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    After analysis and comparison of the problems of the existing one-versus-one (OVO) and one-versus-rest (OVR) decomposition methods of multi-class support vector machine (SVM), the novel strategy based on posterior probability is presented to reconstruct a multi-class classifier from binary SVM-based classifiers. The new reconstruction strategy can increase recognition accuracy and resolve the uncl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nearest Feature Line: A Tangent Approximation

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (140 KB) | HTML iconHTML

    Nearest feature line (NFL) (S.Z. Li and J. Lu, 1999) is an efficient yet simple classification method for pattern recognition. This paper presents a theoretical analysis and interpretation of NFL from the perspective of manifold analysis, and explains the geometric nature of NFL based similarity measures. It is illustrated that NFL, nearest feature plane (NFP) and nearest feature space (NFS) are s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Feature Fusion Algorithm for Human Matching between Non-Overlapping Cameras

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (345 KB)

    Human matching is fundamental in human tracking over non-overlapping cameras. Fusing multiple features is an efficient way to increase the ratio of matching. In this paper, we present an algorithm of iterative widening fusion (IWF) to fuse the multiple features, including color histogram, UV chromaticity, major color spectrum histogram and scale-invariant features (SIFT). Also, the Bayesian framew... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Improved Algorithm for Subpixel Location of Circle Center

    Publication Year: 2008, Page(s):1 - 6
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB)

    To obtain the center of a circle in the digital image with high precision is always the key issue in the target recognition and location. Starting from the subpixel edge location, a improved algorithm for obtaining the subpixel edge, in this paper, is first brought forward based on the geometrical feature of the center and gray-distributed characteristic of the practical image. Then, the center lo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accurate Eye Localization under Large Illumination and Expression Variations with Enhanced Pictorial Model

    Publication Year: 2008, Page(s):1 - 6
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1261 KB)

    As the first step in a face normalization procedure, accurate eye localization technique has the fundamental importance for the performance of face recognition systems. One of the most classical methods to address this is the pictorial model where the appearance model and shape constraints are optimized together. However, under extreme illumination changes and large expression variations, the simp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.