DocumentCode :
2766012
Title :
Connected Numeral Strings Segmentation Based on the Combination of Characteristic Position and Contour Detecting
Author :
Zhang, Tian ; Wang, Xi-chang ; Chen, Chang-hua ; Liu, Jiang
Author_Institution :
Shandong Normal Univ., Jinan, China
fYear :
2009
fDate :
7-9 March 2009
Firstpage :
81
Lastpage :
84
Abstract :
Segmentation of Connected numeral strings plays an important role in number recognition systems. A new method to segment two connected numeral strings is proposed in the article, we define characteristic position first, using it the graph-representation of the image is derived, based on this and using contour detecting we attain the candidate segmentation position pairs used for determining the segmentation path, then a criterion is applied to choose the best segmentation from the candidates. Finally, an experiment is conducted. The results reveal that the method proposed has high speed and good result.
Keywords :
graph theory; image recognition; image segmentation; object detection; contour detection; graph representation; number recognition systems; numeral string segmentation; Character recognition; Digital images; Image edge detection; Image recognition; Image segmentation; Joining processes; Partitioning algorithms; Pixel; Wiener filter; Characteristic position; Connected numeral strings segmentation; Contour detecting; segmentation pair;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Digital Image Processing, 2009 International Conference on
Conference_Location :
Bangkok
Print_ISBN :
978-0-7695-3565-4
Type :
conf
DOI :
10.1109/ICDIP.2009.43
Filename :
5190617
Link To Document :
بازگشت