DMCA
An Adaptive Algorithm for Text Detection from Natural Scenes (2001)
| Venue: | PROCEEDINGS OF COMPUTER VISION AND PATTERN RECOGNITION (CVPR |
| Citations: | 40 - 5 self |
BibTeX
@INPROCEEDINGS{Gao01anadaptive,
author = {Jiang Gao and Jie Yang},
title = {An Adaptive Algorithm for Text Detection from Natural Scenes},
booktitle = {PROCEEDINGS OF COMPUTER VISION AND PATTERN RECOGNITION (CVPR},
year = {2001},
pages = {84--89},
publisher = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present a new adaptive algorithm for automatic detection of text from a natural scene. The initial cues of text regions are first detected from the captured image/video. An adaptive color modeling and searching algorithm is then utilized near the initial text cues, to discriminate text/non-text regions. EM optimization algorithm is used for color modeling, under the constraint of text layout relations for a specific language. The proposed algorithm combines the advantages of several previous approaches for text detection, and utilizes a focus-of-attention approach for text finding. The whole algorithm is applied in a prototype system that can automatically detect and recognize sign input from a video camera, and translate the signs into English text or voice streams. We present evaluation results of our algorithm on this system.
Keyphrases
natural scene text detection adaptive algorithm automatic detection initial cue text layout relation initial text cue em optimization algorithm prototype system whole algorithm text finding english text adaptive color modeling new adaptive algorithm captured image video video camera color modeling sign input focus-of-attention approach text region specific language several previous approach present evaluation result text non-text region voice stream
