Advance Algorithm Based Ancient Tamil Character Recognition By Using MATLAB

L.Suriya Kala, Dr P. Thangaraj


Here this work describes the character recognition process of various ancient Tamil scripts using Hybrid classifier. This work proposed segmentation process for segmenting the individual characters from each other. After segmentation process, an important feature extraction step is used to recognize the Ancient characters accurately. Feature describes the characteristic of object uniquely. Feature extraction is the process of extracting information from test data which is most relevant for classification purpose. Feature Extraction technique extracts the basic components of Tamil Characters in Stone inscription and then it translates the components for further recognition procedures. Finally a recognition system is proposed for the characters recognition in Tamil script of various periods referred to as test data. These test characters are sampled from the script automatically matched with the characters available for different periods using machine intelligence. The proposed Hybrid classifier is tested on quite number samples of ancient Tamil images belonging to different time periods.

Full Text:



Optical Character Recognition for printed Tamil text using Unicode Seethalakshmi et al. / J Zhejiang Univ SCI 2005 6A(11):1297-1305 129

Tamil Handwritten Character Recognition Using Kohonon's Self Organizing Map Dr.J.Venkatesh and C. Sureshkumar IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.12, December 2009


  • There are currently no refbacks.