19 June 2017 Degraded Chinese rubbing images thresholding based on local first-order statistics
Author Affiliations +
Proceedings Volume 10443, Second International Workshop on Pattern Recognition; 1044307 (2017) https://doi.org/10.1117/12.2280301
Event: Second International Workshop on Pattern Recognition, 2017, Singapore, Singapore
Abstract
It is a necessary step for Chinese character segmentation from degraded document images in Optical Character Recognizer (OCR); however, it is challenging due to various kinds of noising in such an image. In this paper, we present three local first-order statistics method that had been adaptive thresholding for segmenting text and non-text of Chinese rubbing image. Both visual inspection and numerically investigate for the segmentation results of rubbing image had been obtained. In experiments, it obtained better results than classical techniques in the binarization of real Chinese rubbing image and PHIBD 2012 datasets.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Fang Wang, Fang Wang, Ling-Ying Hou, Ling-Ying Hou, Han Huang, Han Huang, } "Degraded Chinese rubbing images thresholding based on local first-order statistics", Proc. SPIE 10443, Second International Workshop on Pattern Recognition, 1044307 (19 June 2017); doi: 10.1117/12.2280301; https://doi.org/10.1117/12.2280301
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT


Back to Top