Paper Info
Title
A geometrical method for printed and handwritten Berber character recognition
Abstract
We present an efficient geometrical method based on feature points derived from the skeleton of the normalized image. The type of these points and their relative position in the bounding-rectangle are used to get a code of 27 letters. Noise due to the skew, printing processes and quantization noise of the scanning device are examples of noise sources that may affect the character skeleton, distorting the feature point position. Experimental data with the presence of noise of two pixels on the outline show that the feature-points position can be modified about one pixel or two pixels in horizontal and vertical directions. We can therefore state that, in the case of Berber characters, feature points convey significant information and this approach proved to be very tolerant for a certain degree of variation in input characters
Year
DOI
Venue
1997
10.1109/ICDAR.1997.620564
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference
Keywords
DocType
Volume
computational geometry,document image processing,feature extraction,handwriting recognition,optical character recognition,bounding-rectangle,character skeleton,feature points,geometrical method,handwritten Berber character recognition,horizontal direction,letters,noise,normalized image,pixel,position,printed Berber character recognition,printing processes,quantization noise,scanning device,skew,vertical direction
Conference
2
ISSN
ISBN
Citations 
1520-5363
0-8186-7898-4
0
PageRank 
References 
Authors
0.34
2
3
Name
Order
Citations
PageRank
Djematene, A.100.34
bruno taconet224112.45
Abderrazak Zahour328214.83