7TH CENTURY ANCIENT TAMIL CHARACTER RECOGNITION FROM TEMPLE WALL INSCRIPTIONS

摘要

Recognition of any ancient Tamil characters with respect to any language is complicated, since the ancient Tamil characters differ in written format, intensity, scale, style, and orientation, from person to person. Researchers for the recognition of ancient Tamil languages and scripts are comparatively less with other languages, this is a result of the lack of utilities such as Tamil text databases, dictionaries etc. The problem of ancient Tamil character recognition is the technical challenge than other languages in respects to the similarity and complexity of characters that are composed of circles, holes, loops and curves. Hence ancient Tamil recognition requires more research to reach the ultimate goal of machine simulation of human reading. In this paper, we have made an attempt to recognize ancient Tamil characters by using SIFT features and presented a new and efficient approach based on bag-of key points representation. Collection of SIFT features are first extracted from local patches on the pre-processed images, and they are then quantized by K-means algorithm to form the bag-of-key points representation of the original images. These fixed-length feature vectors are used to classify the characters. A recognition system consists of the activities, namely, digitization, pre-processing, feature extraction and classification. This system achieves a maximum recognition accuracy of 84% using SIFT features.