Pattern recognition and computer vision are the most popular and powerful applications in modern computing industries. They have found wide ranges of applications such as biometrics, biomedical signal classification, industrial automation, and so on. Over the past few decades, researchers in the fields of computers, electrical engineering, and electronics engineering have worked continuously to improve the performances of pattern recognition systems. In spite of these continuous efforts, there is still plenty of scope for new and additional research in these fields. This is due to the popularization of lightweight computing devices, increased customer expectations, and business competitions.

The fifth edition of this handbook compiles the intricacies of pattern recognition and computer vision neatly. Editor C. H. Chen has organized 29 valuable chapters into three parts: “Pattern Recognition Methods and Applications,” “Computer Vision and Image Processing,” and “System, Architecture, and Technology.”

Part 1’s ten chapters cover various pattern recognition methods, such as generative models; supervised, unsupervised, and semi-supervised learning; k-nearest neighbor clustering; random forests; pruning; neural networks; and model adaptation. This part also has various pattern applications such as speech recognition, medical imaging, radar image classification, texture classification, the evaluation of coins, underwater live fish recognition, and emotion recognition in music. Since the book comprehensively covers all three types of learning methods (supervised, unsupervised, semi-supervised learning) with a variety of applications, it can serve as a true handbook for readers. Most of the applications are presented with experimental results and discussions, making the reading fruitful and interesting.

Part 2 also has ten chapters covering diversified topics of computer vision and image processing, including context-assisted methods, statistical shape spaces, tracking systems, knowledge augmented visual learning, graph edit distance, long short-term memory neural networks, morphological representations, sparse representation, manifold learning, and 3D tomosynthesis. All these topics are presented using suitable applications along with experimental results and discussions. The applications presented in this chapter include person identification in surveillance; face recognition; motion-based tracking; facial expression recognition; fingerprint classification; document image analysis; the classification of remote sensing images; brain tumor detection; epilepsy detection; and the detection of multiple sclerosis, Alzheimer’s disease, and breast cancer. Compared to Part 1, Part 2 has a rich set of applications, motivating readers to investigate and explore in depth.

Part 3 has nine chapters covering techniques such as sketch representation, multiple kernel learning, particle swarm optimization, shadow modeling, structured learning, Kalman filtering, and support vector machines. This chapter also has interesting applications and experimental results, as well as discussions to illustrate the working principles of these techniques. The applications considered in this part are content-based image retrieval, face recognition, fault detection in fuel cells, shadow detection, object tracking, automated industrial inspection, and barcode readers. Over and above presenting the techniques along with applications, this chapter touches upon hardware-level architectural details such as VLSI implementation of fuzzy ARTMAP using Vocallo MGW, Atom N270, core i3-530, real-time image processing in embedded systems, and silicon architecture of automata processors.

Overall, this book has a rich set of techniques with a wide range of applications for pattern recognition and computer vision. I have some suggestions for a sixth edition: (1) include a foundation chapter that covers the basics of pattern recognition and computer vision to make the book self-contained; and provide (2) a road map for reading, (3) exercises along with solutions, and (4) keywords for all chapters.

This book will be useful to electrical engineering and computer science graduate students and researchers working in the field of machine vision.