ABSTRACT

In a multi script environment, a collection of documents printed in different scripts is in practice. For automatic processing of such documents through Optical Character Recognition, it is necessary to identify the script type of the document. In this paper, a novel texture-based approach is presented to identify the script type of the documents printed in three prioritized scripts - Kannada, Hindi and English, prevailed in Karnataka, an Indian state. The document images are decomposed through the Wavelet Packet Decomposition using the Haar basis function up to level two. The texture features are extracted from the sub bands of the wavelet packet decomposition. The Shannon entropy value is computed for the set of sub bands and these entropy values are combined to obtain the texture features. Experimentation conducted involved 1500 text images for learning and 1200 text images for testing. Script classification performance is analyzed using the K-nearest neighbor classifier. The average success rate is found to be 99.33%.