Design and Development of Artificial Neural Network Based Tamil Unicode Symbols Identification System
Design and Development of Unicode and its recognition especially for Indian script is an active area of research today. An attempt is made to identify Tamil- a vernacular of southern India, which is also the official language of Tamilnadu. Tamil language present great challenges to an OCR designer due to the large number (247 letters) in the alphabet, the sophisticated ways in which they combine, and the complicated graphemes they result in. The conventional programming methods of mapping symbol images into matrices, analyzing pixel and/or vector data and trying to decide which symbol corresponds to which character would yield little or no realistic results. Clearly the needed methodology will be one that can detect closeness of graphic representations to known symbols based on the character height, character width, the number of horizontal lines (long and short), the number of vertical lines (long and short), number of slope lines, special dots and based on that the glyphs are now set ready for classification. The extracted features are passed to neural network where the characters are classified by supervised learning of Back Propagation algorithm which compromises training, calculation of error, and modifying weights and then testing the given image.and make decisions based on this nearness. This proposed work has employed the MLP technique to identify the symbols, excellent results were obtained for a number of widely used Unicode Tamil font types.
Keywords: Artifical Neural Network , MLP , Unicode , Weights
Download Full-Text
ABOUT THE AUTHOR
Karthick Anand Babu
He is currently working in the area of effective teaching and easy learning methodology. Area of interest includes Neural network,Data mining and Nano computing.
Karthick Anand Babu
He is currently working in the area of effective teaching and easy learning methodology. Area of interest includes Neural network,Data mining and Nano computing.
