A fast text location algorithm in DCT-compressed domain - 文章详情页

作者：

Sun, Hui-Ping (Sun, Hui-Ping.) | Liu, Dang-Hui (Liu, Dang-Hui.) | Shen, Lan-Sun (Shen, Lan-Sun.)

收录：

EI Scopus PKU CSCD

摘要：

A　fast　and　effective　approach　of　automatic　text　localization　in　images　with　complex　background　is　presented.　Text　areas　can　be　segmented　with　an　adaptive　threshold　using　a　new　feature　extracted　from　DCT-compressed　domain,　and　then　a　coarse-to-fine　projecting　and　merging　algorithm　is　proposed　to　locate　the　final　text　area.　Experiments　based　on　JPEG　image　testing　sets　show　its　effective　and　robustness　for　contrast,　language,　and　background　complexity.

关键词：

Algorithms Image processing Feature extraction Image segmentation Optical character recognition Content based retrieval Classification (of information) Threshold voltage Cosine transforms Text processing

作者机构：

[ 1 ] [Sun, Hui-Ping]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100022, China
[ 2 ] [Liu, Dang-Hui]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100022, China
[ 3 ] [Liu, Dang-Hui]Academy of Equipment, Command and Technology, Beijing 101416, China
[ 4 ] [Shen, Lan-Sun]Signal and Information Processing Laboratory, Beijing University of Technology, Beijing 100022, China

通讯作者信息：

电子邮件地址：

查看成果更多字段

成果类型
所属机构

所有年份指定年份从至