Pattern recognition has been a hot field of research in computer science and electrical engineering over the past few decades. Pattern recognition has found many real-world applications using various tools and techniques. Soft computing is widely used in pattern recognition. Soft computing is not one single technique, but rather a collection of techniques including neural networks, fuzzy logic, genetic algorithms, and so on.

This book addresses the use of soft computing techniques for pattern recognition problems, starting with an interesting overview of how the conventional approach to pattern recognition differs from the soft computing approach. Among the various soft computing techniques, the author focuses on fuzzy logic. The major theme of the book relates to pattern recognition approaches based on multidimensional fuzzy implication (MFI). The author presents the conventional interpretation of MFI for pattern recognition problems, and then proposes the need for a new interpretation. The book lays out the constituents of soft computing techniques, including genetic, neurogenetic, and neuro-fuzzy algorithms, along with this new interpretation of MFI. The book achieves a well-balanced treatment of theory, mathematics, and applications. Each chapter has a good number of references, and, except for the introductory chapter, each includes interesting experimental results. In addition, some of the chapters have numerical illustrations and/or case studies. The quality of the technical content is more than excellent.

However, the book also has a few weaknesses. While all of the chapters are well written, they were apparently produced in isolation, thus limiting its cohesiveness. Another minor concern is the very low resolution of the figures. Most of them are unreadable and appear pixelated. Despite these flaws, this book would be useful for research scholars and scientists working in the field of pattern recognition.