Text detection in images based on unsupervised classification of high-frequency wavelet coefficients

被引:102
作者
Gllavata, J [1 ]
Ewerth, R [1 ]
Freisleben, B [1 ]
机构
[1] Univ Siegen, SFB, FK 615, D-57068 Siegen, Germany
来源
PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1 | 2004年
关键词
D O I
10.1109/ICPR.2004.1334146
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Text localization and recognition in images is important for searching information in digital photo archives, video databases and web sites. However, since text is often printed against a complex background, it is often difficult to detect. In this paper, a robust text localization approach is presented, which can automatically detect horizontally aligned text with different sizes, fonts, colors and languages. First, a wavelet transform is applied to the image and the distribution of high-frequency wavelet coefficients is considered to statistically characterize text and non-text areas. Then, the k-means algorithm is used to classify text areas in the image. The detected text areas undergo a projection analysis in order to refine their localization. Finally, a binary segmented text image is generated, to be used as input to an OCR engine. The detection performance of our approach is demonstrated by presenting experimental results for a set of video frames taken from the MPEG-7 video test set.
引用
收藏
页码:425 / 428
页数:4
相关论文
共 12 条
[1]   Text detection for video analysis [J].
Agnihotri, L ;
Dimitrova, N .
IEEE WORKSHOP ON CONTENT-BASED ACCESS OF IMAGE AND VIDEO LIBRARIES (CBAIVL'99) - PROCEEDINGS, 1999, :109-113
[2]  
AGNIHOTRI L, 2003, IN PRESS S SIGN PROC
[3]  
[Anonymous], P ACM INT C DIG LIB
[4]  
GLLAVATA J, P 3 IEEE INT
[5]  
GLLAVATA J, 2004, IN PRESS P 3 INT C I
[6]  
HAO Y, 2003, J WSCG 11 INT C COMP, V11
[7]  
HUA XS, 2000, P 6 INT C DOC AN REC, P545
[8]  
Jain AK, 1998, INT C PATT RECOG, P1497, DOI 10.1109/ICPR.1998.711990
[9]  
LI LH, 1998, P IEEE 1998 WORKSH M, P21
[10]  
Lia J., 1998, IEEE INT C IM PROC, P790