FEATURE EXTRACTION TECHNIQUES FOR HANDWRITTEN CHARACTER RECOGNITION

Abstract

In this era of growing automation, automatic character recognition has become need of the hour. Optical character recognition (OCR) techniques allow computers to recognize handwritten characters and change them in digital format or other formats which are understandable by computers. This automatic recognition requires feature extraction from character images. Feature extraction is a very important phase of character recognition. This paper discusses features based on shapes, skeletons, image moments, image transforms, critical points, etc. This paper also investigates different types of features used in literature works. A good feature set results in good recognition rates. Thus, it is important to have knowledge of different types of features and their properties. This paper benefits its readers by providing them insight of different types of features and helps them in identifying the appropriate feature set according to their application.