Application of Independent Component Analysis in Pattern Recognition and Image Processing using MATLAB
WS256 *You can preview it.
★Includes CD (m-file) *Available for preview.
Chen Yanwei, Ritsumeikan University, College of Information Science and Engineering, Department of Media and Information Studies, Professor (Doctor of Engineering) <Author's Brief Biography> 1985: Graduated from Kobe University, Faculty of Engineering 1987: Completed Master's Program at Osaka University Graduate School of Engineering, Master of Engineering 1990: Completed Doctoral Program at Osaka University Graduate School of Engineering, Doctor of Engineering 1991: Researcher at the Laser Technology Research Institute 1994: Lecturer at the Department of Electrical and Electronic Engineering, University of the Ryukyus 1996: Associate Professor at the Department of Electrical and Electronic Engineering, University of the Ryukyus 2003: Professor at the Department of Electrical and Electronic Engineering, University of the Ryukyus 2004: Professor at the Department of Media and Information Studies, Ritsumeikan University <Publication Date> October 16, 2007 <Price> 52,290 yen (including tax) <Format> B5 size, hardcover, approximately 156 pages
Inquire About This Product
basic information
In an information-oriented society, the media of "images" is becoming increasingly prominent. To enable computers to perform highly flexible and reliable image processing, recognition, and understanding akin to human capabilities, a new image processing method that integrates human visual information processing abilities with learning and adaptation capabilities is necessary. This book explains pattern recognition and image processing using Independent Component Analysis (ICA), which has recently gained attention as a new multidimensional signal analysis method. ICA is formulated as a problem of separating independent source signals from mixed signals that overlap and are observed under various conditions. By extracting features that occur independently from images using ICA, it is possible to represent images efficiently. Additionally, compared to traditional Fourier transforms and wavelet transforms, ICA can extract basis functions that are more suitable for images, allowing for flexible and reliable image processing, recognition, and understanding. This book provides a clear explanation from the basics to applications, incorporating MATLAB simulations.
Price information
52,290 yen (including tax)
Price range
P2
Delivery Time
P2
Applications/Examples of results
Chapter 1: Pattern Recognition and Image Processing through Linear Transformations Chapter 2: Principal Component Analysis (PCA) 1. Formulation and Solution of PCA 2. Example Analysis of Sensory Data using PCA and MATLAB Simulation Chapter 3: Independent Component Analysis (ICA) 1. Formulation of ICA 2. Evaluation Criteria and Solutions for Independence 3. Comparison between ICA and PCA 4. Example of Voice Separation using ICA and MATLAB Simulation Chapter 4: Image Feature Extraction and Modeling using ICA 1. Model for Image Feature Extraction 2. Basis Extraction from Natural Images and MATLAB Simulation 3. Representation of Facial Images and MATLAB Simulation Chapter 5: Applications to Pattern Recognition and Image Processing 1. Face Recognition and MATLAB Simulation 2. Removal of Reflected Light and MATLAB Simulation 3. Image Search based on Color Features and MATLAB Simulation 4. Noise Removal using ICA Shrinkage Filter and MATLAB Simulation Chapter 6: Nonlinearity 1. Kernel PCA 2. Kernel ICA *Includes Sample Programs
catalog（3）
Download All Catalogs
Company information
-
