Computer Interpretation of Imperfect Line Data as a Three-dimensional Scene
Computer Interpretation of Imperfect Line Data as a Three-dimensional Scene

Author: Gilbert Falk

Publisher:

Published: 1970

Total Pages: 406

ISBN-13:

DOWNLOAD EBOOK

The paper describes a heuristic scence description program. This program accepts as input a scene represented as a line drawing. Based on a set of known object models the program attempts to determine the identify and location of each object viewed. The most significant feature of the program is its ability to deal with imperfect input data. Also presented are some preliminary results concerning constraints in projections of planar-faced solids. It is shown that for a restricted class of projections, 4 points located in 3-space in addition to complete monocular information are sufficient to specify all the visible point locations precisely. (Author).

Computer Models of Mind
Computer Models of Mind

Author: Margaret A. Boden

Publisher: Cambridge University Press

Published: 1988-04-29

Total Pages: 306

ISBN-13: 9780521270335

DOWNLOAD EBOOK

This book shows how computer models are used to study many psychological phenomena - including vision, language, reasoning, and learning.

Three-Dimensional Computer Vision
Three-Dimensional Computer Vision

Author: Yoshiaki Shirai

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 308

ISBN-13: 3642824293

DOWNLOAD EBOOK

The purpose of computer vision is to make computers capable of understanding environments from visual information. Computer vision has been an interesting theme in the field of artificial intelligence. It involves a variety of intelligent information processing: both pattern processing for extraction of meaningful symbols from visual information and symbol processing for determining what the symbols represent. The term "3D computer vision" is used if visual information has to be interpreted as three-dimensional scenes. 3D computer vision is more challenging because objects are seen from limited directions and some objects are occluded by others. In 1980, the author wrote a book "Computer Vision" in Japanese to introduce an interesting new approach to visual information processing developed so far. Since then computer vision has made remarkable progress: various rangefinders have become available, new methods have been developed to obtain 3D informa tion, knowledge representation frameworks have been proposed, geometric models which were developed in CAD/CAM have been used for computer vision, and so on. The progress in computer vision technology has made it possible to understand more complex 3 D scenes. There is an increasing demand for 3D computer vision. In factories, for example, automatic assembly and inspection can be realized with fewer con straints than conventional ones which employ two-dimensional computer vision.

Robot Vision
Robot Vision

Author: Berthold Horn

Publisher: MIT Press

Published: 1986

Total Pages: 530

ISBN-13: 9780262081597

DOWNLOAD EBOOK

"Presents a solid framework for understanding existing work and planning future research."--Cover.

Readings in Computer Vision
Readings in Computer Vision

Author: Martin A. Fischler

Publisher: Elsevier

Published: 2014-06-28

Total Pages: 815

ISBN-13: 0080515819

DOWNLOAD EBOOK

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.

AI and Cognitive Science ’89
AI and Cognitive Science ’89

Author: Alan Smeaton

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 347

ISBN-13: 1447131649

DOWNLOAD EBOOK

This volume contains the texts of papers presented at the Second Irish Conference on Artificial Intelligence and Cognitive Science, held at Dublin City University in September 1989. This Conference has now become the major annual forum in Ireland for the presentation and discussion of current research work in the multi-disciplinary area of Artificial Intelligence. Papers in this volume have been divided into seven sections which vary in their subject matter. Image processing, human-computer interaction, planning, applications and theory of expert systems, learn ing, speech, and natural language processing and semantics repre sents as broad a spectrum of AI and AI-related topics as can be found in current AI research. This harmonises quite well with the aims and scope of the AICS'89 conference which were to provide a forum for industry and academic research to discuss AI and AI-related topics and we were delighted that such a broad coverage of topics was achieved. Despite the broad nature, however, none of the papers are primarily review articles; each paper presents new research results within its own specific area.

Computer Identification of Textured Visual Scenes
Computer Identification of Textured Visual Scenes

Author: Ruzena Bajcsy

Publisher:

Published: 1973

Total Pages: 340

ISBN-13:

DOWNLOAD EBOOK

The work deals with computer analysis of textured outdoor scenes involving grass, trees, water and clouds. Descriptions of texture are formalized from natural language descriptions; local descriptors are obtained from the directional and nondirectional components of the Fourier transform power spectrum. Analytic expressions are obtained for orientation, contrast, size, spacing, and in periodic cases, the locations of the choice of sizes is made by a simple higher-level program. The process of region growing is represented by a sheaf-theoretical model which formalizes the operation of pasting local structure (over a window) into global structure (over a region). Programs were implemented which form regions of similar color and similar texture with respect to the local descriptors. (Author Modified Abstract).