Computer vision currently falls short of human vision in two respects; execution time and intelligent interpretation. This book addresses mainly the question of execution time and includes several novel algorithms regarding recognition and interpretation levels. It is based on a workshop on specialized processors for real-time image analysis held as part of the activities of an ESPRIT Basic Research Action, the Working Group on Vision. The aim of the book is to examine the state of the art in machine vision technology, from both hardware and software points of view. The book surveys the new landscape of computer vision for the user of the technology in chapters presenting applications implemented on dedicated or specialized processors. On hardware ranging from VLSI-based architectures to SIMD and MIMD machines, the volume provides a thorough review of applications including target tracking, mobile robot guidance, 3D robot vision, and shape classification. For scientists, engineers, and technicians in or involved with the machine vision community, the book is an invaluable resource for assessing the state of the art in the field and keeping up with new designs and applications.