Morphological waveform coding for writer identification

被引：97

作者：

Zois, EN ^{[1
]}

Anastassopoulos, V ^{[1
]}

机构：

[1] Univ Patras, Dept Phys, Elect Lab, Patras 26500, Greece

来源：

PATTERN RECOGNITION | 2000年 / 33卷 / 03期

关键词：

writer identification; person verification; morphological features; waveform coding;

D O I：

10.1016/S0031-3203(99)00063-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Writer identification is carried out using handwritten text. The feature vector is derived by means of morphologically processing the horizontal profiles (projection functions) of the words. The projections are derived and processed in segments in order to increase the discrimination efficiency of the Feature vector. Extensive study of the statistical properties of the feature space is provided. Both Bayesian classifiers and neural networks are employed to lest the efficiency of the proposed feature. The achieved identification success using a long word exceeds 95%. (C) 2000 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：385 / 398

页数：14