Readings in Computer Vision : Issues, Problem, Principles, and Paradigms

The field of computer vision combines techniques from physics, mathematics, psychology, artificial intelligence, and computer science to examine how machines might construct meaningful descriptions of their surrounding environment. The editors of this volume, prominent researchers and leaders of the SRI International AI Center Perception Group, have selected sixty papers, most published since 1980, with the viewpoint that computer vision is concerned with solving seven basic problems:

• Reconstructing 3D scenes from 2D images
• Decomposing images into their component parts
• Recognizing and assigning labels to scene objects
• Deducing and describing relations among scene objects
• Determining the nature of computer architectures that can support the visual function
• Representing abstractions in the world of computer memory
• Matching stored descriptions to image representation

Each chapter of this volume addresses one of these problems through an introductory discussion, which identifies major ideas and summarizes approaches, and through reprints of key research papers. Two appendices on crucial assumptions in image interpretation and on parallel architectures for vision applications, a glossary of technical terms, and a comprehensive bibliography and index complete the volume.

The field of computer vision combines techniques from physics, mathematics, psychology, artificial intelligence, and computer science to examine how machines might construct meaningful descriptions of their surrounding environment. The editors of this volume, prominent researchers and leaders of the SRI International AI Center Perception Group, have selected sixty papers, most published since 1980, with the viewpoint that computer vision is concerned with solving seven basic problems:

• Reconstructing 3D scenes from 2D images
• Decomposing images into their component parts
• Recognizing and assigning labels to scene objects
• Deducing and describing relations among scene objects
• Determining the nature of computer architectures that can support the visual function
• Representing abstractions in the world of computer memory
• Matching stored descriptions to image representation

Each chapter of this volume addresses one of these problems through an introductory discussion, which identifies major ideas and summarizes approaches, and through reprints of key research papers. Two appendices on crucial assumptions in image interpretation and on parallel architectures for vision applications, a glossary of technical terms, and a comprehensive bibliography and index complete the volume.