模式识别
2006-12
湖南文艺出版社
Nickolay, Bertram 编
773
This book provides a solid statistical foundation for neural networks from a pattern recognition perspective. The focus is on the types of neural nets that are most widely used in practical applications, such as the multi-layer perceptron and radial basis function networks. Rather than trying to cover many different types of neural networks, Bishop thoroughly covers topics such as density estimation, error functions, parameter optimization algorithms, data pre-processing, and Bayesian methods. All topics are organized well and all mathematical foundations are explained before being applied to neural networks. The text is suitable for a graduate or advanced undergraduate level course on neural networks or for practitioners interested in applying neural networks to real-world problems. The reader is assumed to have the level of math knowledge necessary for an undergraduate science degree.
Image Filtering, Restoration and Segmentation Ultrasound Image Denoising by Spatially Varying Frequency Compounding Exploiting Low-Level Image Segmentation for Object Recognition Wavelet Based Noise Reduction by Identification of Correlations Template Based Gibbs Probability Distributions for Texture Modeling and Segmentation Etficient Combination of Probabilistic Sampling Approximations for Robust hnage Segmentation I)iffusion-Like Reconstruction Schemes fi'om Linear Data Models Reduction of Ring Artifacts in High Resolution X-Ray Microtomography hnages A Probabilistic Multi-phase Model for Variational hnage Segmentation Provably Correct Edgel Linking and Subpixel Boundary Reconstruction The Edge Preserving Wiener Filter for Scalar and Tensor Valued Images From Adaptive Averaging to Accelerated Nonlinear Diffusion Filtering Introducing Dynamic Prior Knowledge to Partially-Blurred Image RestorationShape Analysis and Representation On-Line, Incremental Learning of a Robust Active Shape Model Using Irreducible Group Representations for Invariant 3I) Shape Description Shape Matching by Variational Computation of Geodesics on a Manitbld A Modification of the Level Set Speed Function to Bridge Gaps in Data Generation and Initialization of Stable 3D Mass-Spring Models for the Segmentation of the Thyroid Cartilage Preserving Topological Information in the Windowed Hough Transform for Rectangle ExtractionRecognition, Categorization and Detection Fast Scalar and Vectorial Grayscale Based Invariant Features tbr 3D Cell Nuclei Localization and Classification……Computer Vision and Lmage RetrievelAnuthor Index
