Support vector machine-based text detection in digital video

被引：54

作者：

Kim, KI ^{[1
]}

Jung, K ^{[1
]}

Park, SH ^{[1
]}

Kim, HJ ^{[1
]}

机构：

[1] Kyungpook Natl Univ, Dept Comp Engn, Taegu 702701, South Korea

来源：

PATTERN RECOGNITION | 2001年 / 34卷 / 02期

关键词：

support vector machines (SVMs); text detection; texture classification; machine learning; multi-media data retrieval;

D O I：

10.1016/S0031-3203(00)00095-9

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A support vector machine (SVM)-based text detection method for video images is proposed. The method is based on the observation that a SVM has the capability of learning in sparse high-dimensional space and incorporates a feature extraction scheme within its own architecture.

引用

页码：527 / 529

页数：3