Handwritten Tamil Character Recognition and Conversion using Neural Network
Journal Title: International Journal on Computer Science and Engineering - Year 2010, Vol 2, Issue 7
Abstract
Hand written Tamil Character recognition refers to the process of conversion of handwritten Tamil character into Unicode Tamil character. The scanned image is segmented into paragraphs using spatial space detection technique, aragraphs into lines using vertical histogram, lines into words using horizontal histogram, and words into character image glyphs using horizontal histogram. The extracted features considered for recognition are given to Support Vector achine, Self Organizing Map, RCS, Fuzzy Neural Network and Radial Basis Network. Where the characters are classified using supervised learning algorithm. These classes are mapped onto Unicode for recognition. Then the text is reconstructed using Unicode fonts. This character recognition finds applications in document analysis where the handwritten document can be converted to editable printed document. This approach can be extended to recognition and reproduction of hand written documents in South Indian languages. In the training set, a recognition rate of 100% was achieved and in the test set the recognized speed for each character is 0.1sec and accuracy is 97%. derstandably, the training set produced much higher ecognition rate than the test set. Structure nalysis suggested that the proposed system of RCS with back propagation network is given higher recognition rate.
Authors and Affiliations
C. Sureshkumar , Dr. T. Ravichandran
Keywords
Related Articles
- EP ID EP102728
- DOI -
- Views 108
- Downloads 0
Minimizing weighted mean flow time in open shop scheduling with time-dependent weights and intermediate storage cost
Open shop scheduling problem is a common scheduling problem and has wide engineering applications in manufacturing. In some industrial cases, open shop scheduling could be a long scheduling problem as an aircraft product...
The role of Quantum computation in molecular interactions in biological cells
We propose that the interacting molecules in a living cell are databases of quantum superpositions and scan each other for biologically relevant interactions. We discuss our hypothesis in view of the recent findings in w...
Diabetic Retinopathy-Early Detection Using Image Processing Techniques
Abstract - Diabetic retinopathy is the cause for blindness in the human society. Early detection of it prevents blindness. Image processing techniques can reduce the work of ophthalmologists and the tools used automatica...
A New Multi Fractal Dimension Method for Face Recognition with Fewer Features under Expression Variations
In this work, a new method is presented as a mingle of Principal Component Analysis (PCA) and Multi-Fractal Dimension analysis (MFD) for feature extraction. Proposed method makes use of best decision taken from both the...
ENHANCED SECURITY IN SECURE SOCKET LAYER 3.0 SPECIFICATION
We address the issue network security.All the bank provides 128 bit ssl encryption in two way communication between client and server.In this paper we can tell you idea behind 256 ssl encryption.By which two way communic...