Off-line Handwritten Malayalam Character Recognition Using Gabor Filters

Handwritten character recognition is the ability of a Computer to receive and interpret handwritten input. Computers may find difficultly in deciphering many kinds of printed characters which is of different fonts and styles or handwritten characters. This paper focuses on the recognition of handwritten Malayalam characters. The proposed system consists of image acquisition, preprocessing, segmentation, feature extraction, classification & recognition. Here spatial Gabor filters are used to extract the Spatial Gabor based features and also ratios of grid values in horizontal and vertical directions are considered as additional features. The proposed system was tested with different handwritings and better recognition rates obtained. These results are comparable and better than published work in the same area. The experimental results indicate the effectiveness of this method for practical handwritten Malayalam character recognition. Keywords— Character recognition, Pre-processing, Binarization, Feature extraction, Gabor filter