Title :
Reconstruction of character skeletons using Gabor filter features
Author :
Whichello, A.P. ; Yan, Hong
Author_Institution :
Dept. of Electr. Eng., Sydney Univ., NSW, Australia
fDate :
10/26/1995 12:00:00 AM
Abstract :
Features derived from Gabor wavelet filters are used to reconstruct the skeletons of handwritten digits. The features are linked into strokes which are suitable as input to character recognisers. Experimental results are given to show the effectiveness of the stroke-linking algorithm as a thinning method, producing well-connected skeletons for broken and noisy digits
Keywords :
character recognition; feature extraction; filtering theory; handwriting recognition; image reconstruction; wavelet transforms; Gabor wavelet filters; broken digits; character recognition; character skeletons; handwritten digits; noisy digits; reconstruction; stroke-linking algorithm; thinning method;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19951337
