Ranka S., Sahni S. Hypercube Algorithms with Applications to Image Processing and Pattern Recognition

Springer, 1990. — 241 p.This book deals primarily with algorithmic techniques for SIMD and MIMD hypercubes. These techniques are described in detail in Chapter 2 and then used in subsequent chapters. Problems with application to image processing and pattern recognition are used to illustrate the use of the primitive hypercube operations developed in Chapter 2 . The primitive operations of Chapter 2, however, have application to problems from other application areas too. Computational geometry, graph theory, scheduling, and VLSI CAD, are examples of some of the other application areas where these techniques have been applied. In addition to dealing with techniques for fine grained hypercubes, techniques for medium grained hypercubes such as those currently available are also discussed.
This book is suitable for use in a one semester or one quarter course on hypercube algorithms. For students with no prior exposure to parallel algorithms, it is recommended that one week be spent on the material in Chapter 1, approximately six weeks on the material in Chapter 2, and one week on Chapter 3 . The remainder of the term can be spent covering selected topics from the rest of the book.Fundamental Operations
SIMD Matrix Multiplication
One Dimensional Convolution
Template Matching
Hough Transform
Clustering
Image Transformations
SIMD String Editing