7TH CENTURY ANCIENT TAMIL CHARACTER RECOGNITION FROM TEMPLE WALL INSCRIPTIONS
Journal Title: Indian Journal of Computer Science and Engineering - Year 2012, Vol 3, Issue 5
Abstract
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.
Authors and Affiliations
Rajakumar S. , Dr. Subbiah Bharathi V.
Keywords
Related Articles
- EP ID EP86986
- DOI -
- Views 171
- Downloads 0
AN IMPROVEMENT OF MINH’S ALGORITHM FOR GENERATING GAMMA VARIATES WITH ANY VALUE OF SHAPE PARAMETER
The algorithm of Minh as in [Minh (1988)] was used to generate variates having a gamma distribution with shape parameter a>1 only. In this paper, a method, which is the improvement of the algorithm of Minh is introduc...
NON-BLIND IMAGE WATERMARKING USING CONTOURLET TRANSFORM
This paper presents a novel non-blind watermarking algorithm using contourlet transform. The contourlet transform is preferred for watermarking because of its ability to capture the directional edges and contours superio...
OCCLUSION VERIFICATION IN FACE DETECTION AND AGE ESTIMATION USING LOCAL BINARY PATTERN AND DTOD CLASSIFIER USING MORPH DATASET
The purpose of this research work is focused on occlusion conditions in the face like wearing sunglasses and scarf in the eyes and mouth positions of the facial image. The proposed work has three stages. The first stage...
Non-Equilibrium Flow Type Behaviour In Presence Of Transonic Free Streams Probably Caused By Turbulence Modeling Limitations For Base Flow Computations Using N-S Code, As Well As BASE2D Codes.
The computational difficulties in getting the flow field using a RANS solver of base flows is given here in two special cases where results were obtainable only when free stream flow was not considered. The computational...
AN IMPROVEMENT IN LARSA AND ITS IMPLEMENTATION ON ALLOCATION OF SEATS TO CATEGORIES IN AN ORGANIZATION
In this paper, we propose modifications to LaRSA - a fast exact algorithm for the allocation of seat for the EU Parliament. This improvement shall reduce its run time by a considerable amount. Further, we apply this modi...