Title :
Removal of interferential curve from text image
Author :
Cheng, Zhiguo ; Liu, Yuncai
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiao Tong Univ., China
Abstract :
A general algorithm for eliminating interferential curve in text image was proposed, which converted images into basic graph and super graph firstly, and then treated interferential curve as principal curve to detect principal curve in image. In the detection, improved shortest path algorithm and orientation offset algorithm were used, and finally, the detected curve was removed from original image. Experiments conducted with a variety of text images showed that this algorithm is effective for removing interferential curve in text image.
Keywords :
character recognition; object detection; character recognition; interferential curve removal; orientation offset algorithm; principal curve detection; shortest path algorithm; text image; Character recognition; Engineering drawings; Geographic Information Systems; Image converters; Image processing; Image segmentation; Optical character recognition software; Pattern recognition; Text recognition; Videos;
Conference_Titel :
Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on
Print_ISBN :
0-7695-2315-3
DOI :
10.1109/ITCC.2005.243