OCR for Handwritten Kannada Language Script

The optical character recognition (OCR) is the process of converting textual scanned image into a computer editable format. The proposed OCR system is for complex handwritten Kannada characters. One of the major challenges faced by Kannada OCR system is recognition of handwritten text from an image. The input text image is subjected to preprocessing and then converted into binary image. Segmentation process is carried to extract single character from image. This can be done using connected component labeling. Hu’s invariant moments, horizontal and vertical profile features are obtained as features from zoned image. Probabilistic neural network (PNN) classifier is used for character recognition. Finally the recognized output is editable in baraha editor. An accuracy of 94.69% is achieved in character recognition of the domain specific input. Keywords— Optical Character Recognition (OCR), Feature Extraction, Neural Network, Kannada Scripts