DocumentCode :
2146026
Title :
Improving Scene Text Detection by Scale-Adaptive Segmentation and Weighted CRF Verification
Author :
Pan, Yi-Feng ; Zhu, Yuanping ; Sun, Jun ; Naoi, Satoshi
Author_Institution :
Fujitsu R&D Center Co., Ltd., Beijing, China
fYear :
2011
fDate :
18-21 Sept. 2011
Firstpage :
759
Lastpage :
763
Abstract :
This paper presents a hybrid method for detecting and localizing texts in natural scene images by stroke segmentation, verification and grouping. To improve system performance, novelties on two aspects are proposed: 1) a scale-adaptive segmentation method is designed for extracting stroke candidates, and 2) a CRF model with pair-wise weight by local line fitting is designed for stroke verification. Moreover, color-based text region estimation is used to guide segmentation and verification more accurately. Experimental results on ICDAR 2005 competition dataset show that the proposed approach can detect and localize scene texts with high accuracy, even under noisy and complex backgrounds.
Keywords :
formal verification; image recognition; image segmentation; natural scenes; text analysis; ICDAR 2005 competition dataset; color-based text region estimation; local line fitting; natural scene image; scale-adaptive segmentation; scene text detection; stroke grouping; stroke segmentation; stroke verification; weighted CRF verification; Estimation; Feature extraction; Image color analysis; Image edge detection; Image segmentation; Noise; Training; Conditional random field (CRF); Stroke segmentation; Stroke verification; Text detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Document Analysis and Recognition (ICDAR), 2011 International Conference on
Conference_Location :
Beijing
ISSN :
1520-5363
Print_ISBN :
978-1-4577-1350-7
Electronic_ISBN :
1520-5363
Type :
conf
DOI :
10.1109/ICDAR.2011.158
Filename :
6065413
Link To Document :
بازگشت