Feature extraction of handwritten Kannada characters using curvelets and principal component analysis

Optical Character Recognition (OCR) is the well-known software product, which is used to automatically process the document images. It is defined as the process of converting scanned document images of machine printed or handwritten text into a computer editable format. In this paper, Wrapping based Curvelet transform is proposed to perform feature extraction. An attempt is also made to perform dimensionality reduction using principal component analysis. Nearest neighbor classifier is used to recognize the handwritten Kannada characters. The overall accuracy obtained using the proposed method is 90%.