Title :
A multi-resolution based approach for handwriting segmentation in gray-scale images
Author :
Cheriet, M. ; Thibault, R. ; Sabourin, R.
Author_Institution :
Lab. d´´Image et de Modelisation Tridimensionnelle, Ecole de Technol. Superieure, Montreal, Que., Canada
Abstract :
We present a new method to segment visual handwritten data in gray-scale images. In handwriting recognition, visual shapes are very important in improving the system´s performance. We introduce a robust method for extracting visual shapes of handwritten data from a noisy background. We adopted a multi-resolution Marr-Hildreth (1980) based approach to correctly segment visual data in variable contrasted images. Encouraging results have been obtained on real data, from the CEDAR database
Keywords :
edge detection; feature extraction; handwriting recognition; image resolution; image segmentation; CEDAR database; Marr-Hildreth based approach; edge detector; gray-scale images; handwriting recognition; handwriting segmentation; multi-resolution based approach; robust method; system performance; variable contrasted images; visual handwritten data segmentation; visual shapes extraction; Background noise; Data mining; Gray-scale; Handwriting recognition; Image databases; Image segmentation; Multi-stage noise shaping; Robustness; Shape; System performance;
Conference_Titel :
Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6952-7
DOI :
10.1109/ICIP.1994.413295
