BROWSE
Detail
Conference Paper
Cursive Text Line Extraction from the Destination Address Area on Mail Image
Cited - time in 
Share 
Share
- Authors
- Seon Hwa Jeong, Ho Yon Kim
- Issue Date
- 2005-06
- Citation
- International Conference on Imaging Science, Systems, and Technology: Computer Graphics (CISST) 2005, pp.79-85
- Language
- English
- Type
- Conference Paper
- Abstract
- This paper describes a method of separating text lines from cursive Korean address images based on X-Y cut of input image and grouping and splitting of the X-Y cut resulted images. The method is robust to address images which normally appear in the application field. In other words, it can deal with undulated, skewed, vertically contacted or vertically overlapped text lines under a stabilized performance. The experiment done with address images extracted from Korean live mails has demonstrated the superiority of the proposed method. The success rate for the 989 testing images was about 93.1%.
- KSP Keywords
- Success rate, Text Line Extraction, X-Y cut