Handwritten Symbol Recognition Using Hierarchical Shape Representation Model Based on Shape Signature

Abstract

The Signature represents visual object shape 2D contour in 1D to recognition shape of the object. This 1D shape representation translated into Centroid Distance Histogram (CDH) [16] to achieve invariant transformations such as translation, scale, rotation, flip. The CDH representation performs well in content based image retrieval system with low computational complexity and this representation method insensitive to noise of boundary. The CDH fails to represent concave shape object because the signature function maps some of the angle to more than one length from centroid to contour. This problem solved by modifyingthe shape signature function which returns the average centroid length when the angle difference between two contour points is approximately equals to 0.873 by traversing contour points in clockwise direction. The starting point for clock traversing is minimum distance point from centroid to contour. The Average Centroid Lengths (ACL) converted into histogram which makes shape representation independent of transformations. To improve recognition, more information of contour obtainedby first order and second order difference histogram of the modified signature. This first order and second order difference [16] shape signaturerepresented as hierarchical ACL. This ACL representation suitable forthe Handwritten symbol recognition because small changes in contourof shape adopted in Hierarchical ACL representation. The Handwritten symbol recognized based on k-nearest neighbour classifier (k-NNC) on sample database symbols.