Title :
A shape band-pass filter for character recognition and texture segmentation
Author :
Wang, Demin ; Haese-coat, Véronique ; Ronsin, Joseph
Author_Institution :
IRISA, Rennes, France
Abstract :
Character recognition and texture segmentation are performed by a filter based on morphological opening. The filter is characterized by two shape patterns, one of them being larger than the other. If it is applied to an image, the output image will keep only the image objects which are smaller than the large shape pattern but larger that the small one. Thus, the filter has shape band-pass characteristics. It is used for character recognition and texture segmentation. Experimental results show the good performance of the filter for these purposes
Keywords :
band-pass filters; character recognition; document image processing; image segmentation; image texture; mathematical morphology; character recognition; documents; morphological filter; morphological opening; nonlinear filter; shape band-pass filter; template matching; texture segmentation; Band pass filters; Character recognition; Frequency; Image segmentation; Linear systems; Low pass filters; Morphology; Nonlinear filters; Shape; Telephony;
Conference_Titel :
Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-8186-7128-9
DOI :
10.1109/ICDAR.1995.601993
