To search, Click below search items.


All Published Papers Search Service


Accuracy Augmentation of Tamil OCR Using Algorithm Fusion


R.Jagadeesh Kannan, R.Prabhakar


Vol. 8  No. 5  pp. 51-56


The need for OCR arises in the context of digitizing Tamil documents from the ancient and old era to the latest, which helps in sharing the data through the Internet. Tamil, which is a south Indian language, is one of the oldest languages in the world. Even there are few works going on in Tamil OCR, the accuracy of the approaches still remains a challenging area of research. Many of the works related to Tamil OCR have not concentrated or dealt enough with the accuracy parameter. Our work is contributed to increase the performance of Tamil OCR. We have chosen two algorithms to be fused to get the advantage of both the algorithms. Fusing the algorithms yields efficiency of OCR conversion. Improvement in accuracy is proven through experimental results discussed in this paper.


Optical Character Recognition (OCR), Hidden Markov Models (HMM), Support Vector Machines (SVM), Radial Basis Function Neural Network (RBF-NN)