Browse Prior Art Database

COMPUTER ARCHITECTURES FOR IMAGE PROCESING Guest Editor's Introduction

IP.com Disclosure Number: IPCOM000131574D
Original Publication Date: 1983-Jan-01
Included in the Prior Art Database: 2005-Nov-11
Document File: 5 page(s) / 24K

Publishing Venue

Software Patent Institute

Related People

Kai Hwang: AUTHOR [+3]

Abstract

Information scientists have long recognized that ";one picture is worth a thousand words,"; and over the last decade, extensive research and development has been devoted to pattern analysis and image understanding by computers. Practical applications of such computers include the processing of biomedical images for diagnosis; the recognition of characters, figureprints, and moving objects; remote sensing; industrial inspection; robotic vision; military intelligence; and communications data compression. ~

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 21% of the total text.

Page 1 of 5

THIS DOCUMENT IS AN APPROXIMATE REPRESENTATION OF THE ORIGINAL.

This record contains textual material that is copyright ©; 1983 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved. Contact the IEEE Computer Society http://www.computer.org/ (714-821-8380) for copies of the complete work that was the source of this textual material and for all use beyond that as a record from the SPI Database.

COMPUTER ARCHITECTURES FOR IMAGE PROCESING Guest Editor's Introduction

Kai Hwang,

Purdue University

Information scientists have long recognized that "one picture is worth a thousand words," and over the last decade, extensive research and development has been devoted to pattern analysis and image understanding by computers. Practical applications of such computers include the processing of biomedical images for diagnosis; the recognition of characters, figureprints, and moving objects; remote sensing; industrial inspection; robotic vision; military intelligence; and communications data compression. ~

This special issue attempts to bring together a body of work by leading researchers in computer architecture, image processing, pattern recognition, and pictorial database management. The increasing importance of this work lies in both active research results and in the promise of newer, broader applications. I hope that these articles will stimulate further investigations towards the cost-effective development of intelligent image analysis computers, which in turn will bring us closer to our ultimate goal: promoting better man-machine interactions in the era of real-time knowledge information processing.

Intelligent image analysis functions.

The deficiency of today's computers stems mainly from the 1/0 mechanisms: computers still cannot communicate with human beings in natural forms, such as spoken or written languages, pictures or images, documents, and illustrations. Existing computers are far from satisfactory in their 1/0 speed and speech, vision, translation, and realtime responses. To develop "human- oriented" interactive computers we must first upgrade their capability to understand "natural" information representations and then respond to them intelligently and perhaps more reliably than human beings can. Computers with intelligent 1/0 will benefit both professional and nonprofessional computer users.

Three research areas have been identified in the development of intelligent man-machine interfaces: natural language processing, such as designing computers that understand English, Chinese, and other natural languages; speech understanding, which demands both speech analysis and synthesis; and the focus of this issue, image processing and recognition, in which pictorial and imagery data are processed on-line and interactively with high accuracy.

To implement image processing and recognition, we need to develop subsystems for input, output, and analysis of imagery data retrieved from a large image database syst...