跳到主要导航 跳到搜索 跳到主要内容

Scene text detection with superpixels and hierarchical model

  • Xi'an Jiaotong University

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

Scene text detection is a challenging task for the text-based information extraction systems. We present a novel scene text detection method for this task. The images are over-segmented into meaningful perceptron superpixels, and candidate connected components (CCs)are extracted by combining local contrast and color consistency. The non-text components are then pruned by a hierarchical model consisting of three stages in cascade. Experimental results show that our approach is better than other state-of-the-art methods.

源语言英语
主期刊名2012 IEEE International Conference on Image Processing, ICIP 2012 - Proceedings
1001-1004
页数4
DOI
出版状态已出版 - 2012
活动2012 19th IEEE International Conference on Image Processing, ICIP 2012 - Lake Buena Vista, FL, 美国
期限: 30 9月 20123 10月 2012

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
ISSN(印刷版)1522-4880

会议

会议2012 19th IEEE International Conference on Image Processing, ICIP 2012
国家/地区美国
Lake Buena Vista, FL
时期30/09/123/10/12

学术指纹

探究 'Scene text detection with superpixels and hierarchical model' 的科研主题。它们共同构成独一无二的学术指纹。

引用此