AUTOMATED EVALUATION OF OCR ZONING

被引：55

作者：

KANAI, J ^{[1
]}

RICE, SV ^{[1
]}

NARTKER, TA ^{[1
]}

NAGY, G ^{[1
]}

机构：

[1] RENSSELAER POLYTECH INST,DEPT ECSE,TROY,NY 12180

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1995年 / 17卷 / 01期

关键词：

DOCUMENT IMAGE UNDERSTANDING; PAGE SEGMENTATION; LAYOUT ANALYSIS; PERFORMANCE EVALUATION METRIC;

D O I：

10.1109/34.368146

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

Many current optical character recognition (OCR) systems attempt to decompose printed pages into a set of zones, each containing a single column of text, before converting the characters into coded form. We present a methodology for automatically assessing the accuracy of such decompositions, and demonstrate its use in evaluating six OCR systems.

引用

页码：86 / 90

页数：5