RECOGNITION TECHNOLOGY FRONTIERS

被引：5

作者：

BAIRD, HS

机构：

[1] AT and T Bell Laboratories, 600 Mountain Avenue, Room 2C-322, Murray Hill

来源：

PATTERN RECOGNITION LETTERS | 1993年 / 14卷 / 04期

关键词：

RECOGNITION; POSTAL ADDRESS; TRAINABLE SYSTEMS;

D O I：

10.1016/0167-8655(93)90098-X

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Rapid improvements in hardware and algorithms are reshaping the technological basis of postal address recognition. An increasingly important theme is automation of the engineering process itself. through trainable classifiers, realistic distortion models, and statistical contextual analysis. Relevant basic research at AT&T Bell Laboratories includes VLSI neural networks. algorithmic pattern recognition, computational linguistics, and artificial intelligence. Interdisciplinary application of these has stimulated improvements in handwritten ZIP code recognition, machine-print address recognition, and address block location.

引用

页码：327 / 334

页数：8

共 16 条

[1] FEATURE IDENTIFICATION FOR HYBRID STRUCTURAL STATISTICAL PATTERN-CLASSIFICATION [J].

BAIRD, HS .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1988, 42 (03) :318-333

[2] READING CHESS [J].

BAIRD, HS ;

THOMPSON, K .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (06) :552-559

[3]

BAIRD HS, 1988, 1988 P IAPR WORKSH S

[4]

BAIRD HS, 1990, 1990 P IAPR WORKSH M

[5]

BAIRD HS, 1990, 1990 P IAPR WORSKH S

[6]

BAIRD HS, 1987, 1987 P C SOC PHOT SC

[7]

BAIRD HS, 1991, 1ST P INT C DOC AN R

[8]

BOSE C, UNPUB IEEE T PATTERN

[9]

BOSER B, 1991, ISSCC, P184

[10]

JACKEL LD, 1990, P IEEE INT C SYST MA

← 1 2 →