Title :
Automatic text location in natural scene images
Author :
Li, Chuang ; Ding, Xiaoqing ; Wu, Youshou
Author_Institution :
Image Process. Div., Tsinghua Univ., Beijing, China
fDate :
6/23/1905 12:00:00 AM
Abstract :
A new connected component based segmentation algorithm which automatically extracts text regions from natural scene images is proposed in this paper. This approach utilizes a multichannel decomposition method to locate text blocks in complex backgrounds. Block alignment analysis and recognition confidence values are used in the combination and identification of the connected components. The algorithm is applied to a test image database and shows promising results
Keywords :
image segmentation; optical character recognition; automatic text location; block alignment analysis; connected component based segmentation algorithm; multichannel decomposition method; natural scene images; text region extraction; Color; Filtering; Flowcharts; Image converters; Image recognition; Layout; Optical character recognition software; Quantization; Roads; Text recognition;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953950
