A Survey of Feature Extraction Methods for Handwritten Devnagari Character Recognition

In India, Devanagari script is used by more than 300 million people. There has been a significant improvement in the research related to the recognition of handwritten Devanagari characters in the past few years. But accurate handwritten character recognition is a difficult task due to variations in shapes of the same character with different writer. Selection of feature extraction is the most important factor in achieving high recognition performance in Optical Character Recognition (OCR) systems. This paper presents review on different feature extraction methods for off-line handwritten Devnagari OCR. The feature extraction methods are discussed based on Statistical, Structural, and Global transformation and moments. Along with feature-extraction methods Preprocessing, Segmentation, and Classification techniques useful for the recognition are discussed in various sections of the paper. An attempt is made to address the recognition rates of these feature extraction methods and finally research scope in the Devnagari OCR is discussed. Moreover, the paper also contains an ample bibliography of many selected papers as an aid for the researchers working in the field of Devanagari OCR.