Computer Vision and Image Processing: Fundamentals and Applications

Description

The book familiarizes readers with fundamental concepts and issues related to computer vision and major approaches that address them. The focus of the book is on image acquisition and image formation models, radiometric models of image formation, image formation in the camera, image processing concepts, concept of feature extraction and feature selection for pattern classification/recognition, and advanced concepts like object classification, object tracking, image-based rendering, and image registration. Intended to be a companion to a typical teaching course on computer vision, the book takes a problem-solving approach. Cover Half Title Title Page Copyright Page Dedication Contents Preface Author Part I: Image Formation and Image Processing 1. Introduction to Computer Vision and Basic Concepts of Image Formation 1.1 Introduction and Goals of Computer Vision 1.2 Image Formation and Radiometry 1.2.1 Image formation 1.2.2 Radiometric quantities 1.2.3 Shape from shading 1.2.4 Photometric stereo 1.3 Geometric Transformation 1.3.1 2D transformations 1.3.2 3D transformations 1.4 Geometric Camera Models 1.4.1 Single camera setup of image formation 1.4.2 Image formation in a stereo vision setup 1.4.3 Basics of stereo correspondence 1.4.4 Issues related to accurate disparity map estimation 1.5 Image Reconstruction from a Series of Projections 1.5.1 Inverse Radon transform - back-projection method 1.5.2 Inverse Radon transform - Fourier transform method 1.6 Summary 2. Image Processing Concepts 2.1 Fundamentals of Image Processing 2.1.1 Point operations 2.1.2 Geometric operations 2.1.3 Spatial or neighbourhood operations 2.1.4 Operations between images 2.2 Image Transforms 2.2.1 Discrete fourier transform 2.2.2 Discrete cosine transform 2.2.3 K-L transform 2.2.4 Wavelet transform 2.2.5 Curvelet transform 2.2.6 Ridgelet transform 2.2.7 Shearlet transform 2.2.8 Contourlet transform 2.3 Image Filtering 2.3.1 Spatial domain filtering 2.3.2 Frequency domain filtering 2.3.3 Homomorphic filtering 2.3.4 Wiener filter for image restoration 2.4 Colour Image Processing 2.4.1 Colour models 2.4.2 Colour constancy 2.4.3 Colour image enhancement and filtering 2.4.4 Colour balancing 2.4.5 Pseudo-colouring 2.5 Mathematical Morphology 2.5.1 Binary morphological operations 2.5.2 Applications of binary morphological operations 2.5.3 Grayscale morphological operations 2.5.4 Distance transformation 2.6 Image Segmentation 2.6.1 Thresholding 2.6.2 Region-based segmentation methods 2.6.3 Edge detection-based segmentation 2.6.4 Deformable models for image segmentation 2.7 Summary Part II: Image Features 3. Image Descriptors and Features 3.1 Texture Descriptors 3.1.1 Texture representation methods 3.1.2 Gabor filter 3.1.3 MPEG-7 homogeneous texture descriptor 3.1.4 Local binary patterns 3.2 Colour Features 3.3 Edge Detection 3.3.1 Gradient-based methods 3.3.2 Laplacian of Gaussian operator 3.3.3 Difference of Gaussian operator 3.3.4 Canny edge detector 3.3.5 Hough transform for detection of a line and other shapes 3.4 Object Boundary and Shape Representations 3.4.1 Chain code and shape number 3.4.2 Fourier descriptors 3.4.3 Boundary representation by B-spline curves 3.4.4 MPEG-7 contour-based shape descriptor 3.4.5 Moment invariants 3.4.6 Angular radial transform shape descriptor 3.5 Interest or Corner Point Detectors 3.5.1 SUSAN edge and corner point detector 3.5.2 Moravec corner detector 3.5.3 Harris corner detector 3.5.4 Hessian corner detector 3.6 Histogram of Oriented Gradients 3.7 Scale Invariant Feature Transform 3.8 Speeded up Robust Features 3.9 Saliency 3.10 Summary Part III: Recognition 4. Fundamental Pattern Recognition Concepts 4.1 Introduction to Pattern Recognition 4.2 Linear Regression 4.3 Basic Concepts of Decision Functions 4.3.1 Linear discriminant functions for pattern classification 4.3.2 Minimum distance classifier 4.4 Elementary Statistical Decision Theory 4.5 Gaussian Classifier 4.6 Parameter Estimation 4.6.1 Parametric approaches 4.6.2 Non-parametric approaches 4.7 Clustering for Knowledge Representation 4.8 Dimension Reduction 4.8.1 Unsupervised linear dimension reduction 4.8.2 Supervised linear dimension reduction 4.8.3 Semi-supervised linear dimension reduction 4.9 Template Matching 4.9.1 Finding patterns in an image 4.9.2 Shape similarity measurement by Hausdorff distance 4.9.3 Matching of temporal motion trajectories 4.10 Artificial Neural Network for Pattern Classification 4.10.1 Simple ANN for pattern classification 4.10.2 Supervised learning 4.10.3 Unsupervised learning 4.11 Convolutional Neural Networks 4.11.1 Convolutional layer 4.11.2 Pooling layer 4.11.3 Fully connected layer 4.12 Autoencoder 4.13 Summary Part IV: Applications 5. Applications of Computer Vision 5.1 Machine Learning Algorithms and their Applications in Medical Image Segmentation 5.1.1 Clustering for image segmentation 5.1.2 Supervised clustering for image segmentation 5.1.3 Graph partitioning methods 5.1.4 Image segmentation by neural networks 5.1.5 Deformable models for image segmentation 5.1.6 Probabilistic models for image segmentation 5.1.7 Basics of MRF 5.1.8 Conclusion 5.2 Motion Estimation and Object Tracking 5.2.1 Overview of a video surveillance system 5.2.2 Background subtraction and modeling 5.2.3 Object tracking 5.2.4 Kanade-Lucas-Tomasi tracker 5.2.5 Mean shift tracking 5.2.6 Blob matching 5.2.7 Tracking with Kalman filter 5.2.8 Tracking with particle filter 5.2.9 Multiple camera-based object tracking 5.2.10 Motion estimation by optical flow 5.2.11 MPEG-7 motion trajectory representation 5.2.12 Conclusion 5.3 Face and Facial Expression Recognition 5.3.1 Face recognition by eigenfaces and fisherfaces 5.3.2 Facial expression recognition system 5.3.3 Face model-based FER 5.3.4 Facial expression parametrization 5.3.5 Major challenges in recognizing facial expressions 5.3.6 Conclusion 5.4 Gesture Recognition 5.4.1 Major challenges of hand gesture recognition 5.4.2 Vision-based hand gesture recognition system 5.4.3 Conclusion 5.5 Image Fusion 5.5.1 Image fusion methods 5.5.2 Performance evaluation metrics 5.5.3 Conclusion 5.6 Programming Examples Bibliography Index