Digital Image Processing, Global Edition, 4th edition

For courses in Image Processing and Computer Vision.

Introduce your students to image processing with the industry’s most prized text

For 40 years, Image Processing has been the foundational text for the study of digital image processing. The book is suited for students at the college senior and first-year graduate level with prior background in mathematical analysis, vectors, matrices, probability, statistics, linear systems, and computer programming. As in all earlier editions, the focus of this edition of the book is on fundamentals.

The 4th Edition, which celebrates the book’s 40th anniversary, is based on an extensive survey of faculty, students, and independent readers in 150 institutions from 30 countries. Their feedback led to expanded or new coverage of topics such as deep learning and deep neural networks, including convolutional neural nets, the scale-invariant feature transform (SIFT), maximally-stable extremal regions (MSERs), graph cuts, k-means clustering and superpixels, active contours (snakes and level sets), and exact histogram matching. Major improvements were made in reorganizing the material on image transforms into a more cohesive presentation, and in the discussion of spatial kernels and spatial filtering. Major revisions and additions were made to examples and homework exercises throughout the book.

• Timely, highly readable, and heavily illustrated with numerous examples of practical significance.
  • NEW! This edition contains 5 new images, 35 new drawings, and new exercises.
• Focuses on the fundamental material whose scope of application is not limited to the solution of specialised problems
• Updated with feedback from an extensive survey that involved faculty, students, and independent readers of the book in 5 institutions from 3 countries.
  • UPDATED! A complete update of the image pattern recognition chapter to incorporate new material on deep neural networks, back propagation, deep learning, and, especially, deep convolutional neural networks.
  • EXPANDED! Coverage of feature extraction, including the Scale Invariant Feature Transform SIFT, MSERs, and corner detection.
  • NEW! Coverage of graph cuts and their application to segmentation.
  • NEW! A discussion of superpiels and their use in region segmentation.
  • NEW! An introduction to segmentation using active contours (snakes and level sets).
  • NEW! Material related to each histogram matching.
  • EXPANDED! Coverage of the fundamentals of spatial filtering, image transforms, and finite differences with a focus on edge detection.
• NEW! Two new chapters:
  • A chapter dealing with active contours for image segmentation, including snakes and level sets.
  • A chapter that brings together wavelets, several new transforms, and many of the image transforms that were scattered throughout the book.
• NEW! MATLAB projects, located at the end of every chapter and are structured in a unique way that gives instructors significant flexibility in how projects are assigned.
  • The MATLAB functions required to solve all the projects in the book are provided in executable, p-code format which makes it possible for projects to be assigned solely for the purpose of experimenting with image processing concepts, without having to write a single line of code.

About the Book

• A complete update of the image pattern recognition chapter to incorporate new material, including deep neural networks, backpropagation, deep learning, and, especially, deep convolutional neural networks.
• Expanded coverage of feature extraction, including maximally stable extremal regions, and the Scale Invariant Feature Transform (SIFT).
• A discussion of superpixels and their use in region segmentation.
• Coverage of graph cuts and their application to segmentation.
• New material related to histogram matching.
• Expanded coverage of the fundamentals of spatial filtering.
• A more comprehensive and cohesive coverage of image transforms.
• A more complete presentation of finite differences, with a focus on edge detection.
• More homework problems at the end of the chapters.
• More examples.

Content updates

· Chapter 1: Some figures were updated and parts of the text were rewritten to correspond to changes in later chapters.

· Chapter 2: A new section dealing with random numbers and probability, with an emphasis on their application to image processing. Many sections and examples were rewritten for clarity.

· Chapter 3: A new section on exact histogram matching, a discussion on separable filter kernels, expanded coverage on the properties of lowpass Gaussian kernels, and highpass, bandreject, and bandpass filters.

· Chapter 4: Several sections were revised to improve the clarity of presentation.

· Chapter 5: Clarifications and a few corrections in notation.

· Chapter 6: Material dealing with color image processing was moved to this chapter. Several sections were clarified, and the explanation of the CMY and CMYK color models was expanded.

· Chapter 7: A new chapter that brings together wavelets, several new transforms, and many of the image transforms that were scattered throughout the book. The emphasis of this chapter is on a cohesive presentation of these transforms from a unified point of view.

· Chapter 8: Numerous clarifications and minor improvements to the presentation.

· Chapter 9: A complete rewrite of several sections, including redrafting of several line drawings.

· Chapter 10: Several sections were rewritten for clarity. Updated the chapter by adding coverage of finite differences, K-means clustering, superpixels, and graph cuts.

· Chapter 11: Updated with numerous topics, improvements in the clarity of presentation, added coverage of slope change codes, expanded explanation of skeletons, medial axes, and the distance transform, and new basic descriptors of compactness, circularity, and eccentricity. New material includes coverage of the Harris-Stephens corner detector, and a presentation of maximally stable extremal regions. A major addition to the chapter is a comprehensive discussion dealing with the Scale-Invariant Feature Transform (SIFT).

· Chapter 123: Now includes coverage of deep convolutional neural networks, an extensive rewrite of neural networks, deep learning, and a comprehensive discussion on fully-connected, deep neural networks that includes derivation of backpropagation starting from basic principles.