Image Processing: Analysis and Machine Vision (Chapman & Hall Computing) [Paperback]

This book is OK as a rather non-mathematical introduction to image processing at an advanced undergraduate level.
The "analog" approach to signal and image processing is not covered extensively. There is more emphasis on algorithmic aspects. Frequency analysis is kept to a minimum and one-dimensional signals such as speech are not covered extensively or at all, although some aspects of analog processing are more easily explained in a 1-D context.
Maybe just as well from an image analysis/computer vision standpoint. Indeed, many other textbooks exist with more emphasis on base functions and transforms (but then they are utterly lacking in the algorithmic approach).

More down to earth, though. I know that my students would be turned off by the US price of $115. Hardly appropriate for the less affluent student ! Especially since the UK Amazon price is £37. Same ISBN. Luckily, in Europe, we can order from the UK store.

I really love this book as far as having many algorithms in the area of image analysis and computer vision spelled out in both mathematical terms and algorithmic steps. Just about every subsection of the book has the format of mathematical equations that perform a particular vision task followed by the algorithm in numbered steps and accompanied by very good figures. What is lacking is any explanation on what is going on as well as a "big picture" viewpoint - why would you want to perform this transform in the first place? For those of us who know the whys and just need the hows, this is a great book. For the novice and the student, I can just imagine this book would be incomprehensible as a textbook. This book is also recommended to students taking a college course in robotics. Most robotics texts give you plenty of narrative on subjects such as the kalman filter or particle filter, but fail to deliver the goods on how to do it. This book gets you there. The product description does not list the table of contents, so I do that next. Note that I am reviewing the third edition, published in 2007.

1. Introduction
Motivation / Why is Computer Vision Difficult? / Image Representation and Image Analysis Tasks / Summary / References

2. The Image, its Representations and Properties
Image Representations, a Few Concepts / Image Digitization / Sampling / Quantization / Digital Image Properties / Metric and Topological Properties of Digital Images / Histograms / Entropy / Visual Perception of the Image / Image Quality / Noise in Images / Color Images / Physics of Color / Color Perceived by Humans / Color Spaces / Palette Images / Color Constancy / Cameras: An Overview / Photosensitive Sensors / A Monochromatic Camera / A Color Camera / Summary / References

3. The Image, its Mathematical and Physical Background
Overview / Linearity / The Dirac Distribution and Convolution / Linear Integral Transforms / Images as Linear Systems / Introduction to Linear Integral Transforms / 1D Fourier Transform / 2D Fourier Transform / Sampling and the Shannon Constraint / Discrete Cosine Transform / Wavelet Transform / Eigen-Analysis / Singular Value Decomposition / Principle Component Analysis / Other Orthogonal Image Transforms / Images as Stochastic Processes / Image Formation Physics / Images as Radiometric Measurements / Image Capture and Geometric Optics / Lens Aberrations and Radial Distortion / Image Capture from a Radiometric Point of View / Surface Reflectance / Summary / References

4. Data Structures for Image Analysis
Levels of Image Data Representation / Traditional Image Data Structures / Matrices / Chains / Topological Data Structures / Relational Structures / Hierarchical Data Structures / Pyramids / Quadtrees / Other Pyramidal Structures / Summary / References

5. Image Pre-Processing
Pixel Brightness Transformations / Position-Dependent Brightness Correction / Gray-Scale Transformation / Geometric Transformations / Pixel Co-ordinate Transformations / Brightness Interpolation / Local Pre-Processing / Image Smoothing / Edge Detectors / Zero-Crossings of the Second Derivative / Scale in Image Processing / Canny Edge Detection / Parametric Edge Models / Edges in Multi-Spectral Images / Local Detection by Local Pre-Processing Operators / Detection of Corners (Interest Points) / Detection of Maximally Stable Extremal Regions / Image Restoration / Degradations That are Easy to Restore / Inverse Filtration / Wiener Filtration / Summary / References

6. Segmentation I
Thresholding / Threshold Detection Methods / Optimal Thresholding / Multi-Spectral Thresholding / Edge Based Segmentation / Edge Image Thresholding / Edge Relaxation / Border Tracing / Border Detection as graph Searching / Border Detection as Dynamic Programming / Hough Transforms / Border Detection Using Border Location Information / Region Construction from Borders / Region Based Segmentation / Region Merging / Region Splitting / Splitting and Merging / Watershed Segmentation / Region Growing Post-Processing / Matching / Matching Criteria / Control Strategies of Matching / Evaluation Issues in Segmentation / Supervised Evaluation / Unsupervised Evaluation / Summary / References

7. Segmentation II
Mean Shift Segmentation / Active Contour Models - Snakes / Traditional Snakes and Balloons / Extensions / Gradient Vector Flow Snakes / Geometric Deformable Models - Level Sets and Geodesic Active Contours / Fuzzy Connectivity / Towards 3D Graph-Based Image Segmentation / Simultaneous Detection of Border Pairs / Sub-optimal Surface Detection / Graph Cut Segmentation / Optimal Single and Multiple Surface Segmentation / Summary / References

8. Shape Representation and Description
Region Identification / Contour-Based Shape Representation and Description / Chain Codes / Simple Geometric Border Representation / Fourier Transforms of Boundaries / Boundary Description using Segment Sequences / B-Spline Representation / Other Contour-Based Shape Description Approaches / Shape Invariants / Region-Based Shape Representation and Description / Simple Scalar Region Descriptors / Moments / Convex Hull / Graph Representation Based on Region Skeleton / Region Decomposition / Region Neighborhood Graphs / Shape Classes / Summary / References

9. Object Recognition
Knowledge Representation / Statistical Pattern Recognition / Classification Principles / Classifier Setting / Classifier Learning / Support Vector Machines / Cluster Analysis / Neural Nets / Feed-Forward Networks / Unsupervised Learning / Hopefield Neural Nets / Syntactic Pattern Recognition / Grammars and Languages / Syntactic Analysis, Syntactic Classifier / Syntactic Classifier Learning, Grammar Inference / Recognition as Graph Matching / Isomorphism of Graphs and Sub-Graphs / Similarity of Graphs / Optimization Techniques in Recognition / Genetic Algorithms / Simulated Annealing / Fuzzy Systems / Fuzzy Sets and Fuzzy Membership Functions / Fuzzy Set Operators / Fuzzy reasoning / Fuzzy System Design and Training / Boosting in Pattern Recognition / Summary / References

10. Image Understanding
Image Understanding Control Strategies / Parallel and Serial Processing Control / Hierarchical Control / Bottom-Up Control / Model-Based Control / Combined Control / Non-Hierarchical Control / RANSAC: Fitting via Random Sample Consensus / Point Distribution Models / Active Appearance Models / Pattern Recognition Methods in Image Understanding / Classification-Based Segmentation / Contextual Image Classification / Boosted Cascade of Classifiers for Rapid Object Detection / Scene Labeling and Constraint Propagation / Discrete Relaxation / Probabilistic Relaxation / Searching Interpretation Trees / Semantic Image Segmentation and Understanding / Semantic Region Growing / Genetic Image Interpretation / Hidden Markov Models / Coupled HMMs / Bayesian Belief Networks / Gaussian Mixture Models and Expectation-Maximization / Summary / References

11. 3D Vision, Geometry
3D Vision Tasks / Marr's Theory / Other Vision Paradigms: Active and Purposive Vision / Basics of Projective Geometry / Points and Hyperplanes in Projective Space / Homography / Estimating Homography from Point Correspondences / A Single Perspective Camera / Camera Model / Projection and Back-Projection in Homogeneous Coordinates / Camera Calibration from a Known Scene / Scene Reconstruction from Multiple Views / Triangulation / Projective Reconstruction / Matching Constraints. Bundle Adjustment / Upgrading the Projective Reconstruction, Self Calibration / Two Cameras, Stereopsis / Epipolar Geometry; Fundamental Matrix / Relative Motion of the Camera; Essential Matrix / Decomposing the Fundamental Matrix from Point Correspondences / Rectified Configuration of Two Cameras / Computing Rectification / Three Cameras and Trifocal Tensor / Stereo Correspondence Algorithms / Active Acquisition of Range Images / 3D Information from Radiometric Measurements / Shape from Shading / Photometric Stereo / Summary / References

12. Use of 3D Vision
Shape from X / Shape from Motion / Shape from Texture / Other Shape from X Techniques / Full 3D Objects / 3D Objects, Models, and Related Issues / Line Labeling / Volumetric Representation, Direct Measurements / Volumetric Modeling Strategies / Surface Modeling Strategies / Registering Surface Patches and their Fusion to get a Full 3D Model / 3D Model-Based Vision / General Considerations / Goad's Algorithm / Model-Based Recognition of Curved Objects from Intensity Images / Model-Based Recognition Based on Range Images / 2D View-Based Representations of a 3D Scene / Viewing Space / Multi-View Representations and Aspect Graphs / Geons as a 2D View-based Structural Representation / Visualizing 3D Real-World Scenes Using Stored Collections of 2D Views / 3D Reconstruction from an Unorganized Set of 2D Vies - A Case Study / Summary / References

13. Mathematical Morphology
Basic Morphological Concepts / Four Morphological Principles / Binary Dilation and Erosion / Hit or Miss Transformation / Opening and Closing / Gray-Scale Dilation and Erosion / Top Surface, Umbra, and Gray-Scale Dilation and Erosion / Umbra Homeomorphism Theorem, Properties of Erosion and Dilation, Opening and Closing / Top Hat Transformation / Skeletons and Object Marking / Homotopic Transformations / Skeleton, Maximal Ball / Thinning, Thickening, and Homotopic Skeleton / Quench Function, Ultimate Erosion / Ultimate Erosion and Distance Functions / Geodesic Transformations / Morphological Reconstruction / Granulometry / Morphological Segmentation and Watersheds / Particles Segmentation, Marking, and Watersheds / Binary Morphological Segmentation / Gray-Scale Segmentation, Watersheds / Summary / References

14. Image Data Compression
Image Data Properties / Discrete Image Transforms in Image Data Compression / Predictive Compression methods / Vector Quantization / Hierarchical and Progressive Compression Methods / Comparison of Compression Methods / Other Techniques / Coding / JPEG and MPEG - Still Image Compression / JPEG - 2000 Compression / MPEG - Full Motion Video Compression / Summary / References

15. Texture
Statistical Texture Description / Methods Based on Spatial Frequencies / Co-occurrence Matrices / Edge Frequency / Primitive Length (Run Length) / Laws' Texture Energy Measures / Fractal Texture Description / Multiscale Texture Description - Wavelet Domain Approaches / other Statistical Methods of Texture Description / Syntactic Texture Description Methods / Shape Chain Grammars / Graph Grammars / Primitive Grouping in Hierarchical Textures / Hybrid Texture Description methods / Texture Recognition Method Applications / Summary / References

16. Motion Analysis
Differential Motion analysis Methods / Optical Flow Computation / Global and Local Optical Flow Estimation / Combined Local - Global Optical Flow Estimation / Optical Flow in Motion Analysis / Analysis Based on Correspondence of Interest Points / Detection of Interest Points / Detection of Interest Points / Correspondence of Interest Points / Detection of Specific Motion Patterns / Video Tracking / Background Modeling / Kernel-Based Tracking / Object Path Analysis / Motion Models to Aid Tracking / Kalman Filters / Particle Filters / Summary / References

I found this book too mathematical and very sparse when actually trying to help myself on an image processing course. It covers quite a lot of ground, but there's almost more math than english. You get the feeling the authors are very comfortable with this, and to be honest if you have done a maths-based degree it'll be fine for you. But then again, you may find it treats topics lightly and constantly refers to other papers, as if you live in a good science library or something.