Features Extraction for Offline Handwritten Character Recognition

Offline handwritten character recognition has been one of the most challenging research areas in the field of image processing and pattern recognition in the recent years. Handwritten character recognition is a very problematic research area because writing styles may vary from one user to another. This paper throws light on four different feature techniques, Zoning, Profile projection, Freeman chain code and Histograms of oriented gradients for handwritten vowels recognition. The recognition is carried out in this work through K nearest neighbors and fuzzy min max classification methods. The best recognition rate of 96 % was obtained using Histogram of oriented gradients features.