Paper Details: Downloads: 305
Serial Number: P1150527004
Title: On-line Structural Approach for Recognizing Hand-Written Indian Numbers
Authors: Ibrahiem M. M. El Emary and Mustafa M. Hammad
Abstract: In this paper, a structural pattern recognition approach is proposed to identify on-line handwritten Indian numbers. The proposed technique depends on the direction between the current pixel and the next new pixel that drawn by the user. Then, use this directions sequence to extract the shape’s primitives. Matching process uses the predefined models of sorted primitives for each digit to identify it. Experimental results show that the recognition rate is 94.87% for the drawn shapes. When the rejected cases are excluded from the calculation, the rate can be increased to 98.07%.
Keywords: Structural pattern recognition; Primitives extractions; On-line handwritten Indian numbers.
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 5
Issue: 7
Submission Date: 5/1/2005 12:00:00 AM
Review Date: 6/1/2005 12:00:00 AM
Publishing Date: 7/1/2005 12:00:00 AM
Article Downloads: 305
Download:

Facebook