Myanmar Alphabet Recognition System Based on Artificial Neural Network

This paper describes Myanmar Alphabet Recognition System Based on Neural Network. Typical pattern recognition systems are designed using two parts. The first part is a feature extractor that finds features within the data, which are specific to the task being solved. Edge detection method is used to extract image' features. It may be grouped into two categories, gradient and Laplacian. The gradient method (Roberts, Prewitt, Sobel) detects the edges by looking for the maximum and minimum in the first derivative of the image. In this paper, Sobel edge operator is chosen because it can generate the significant features for Myanmar Alphabet than other techniques. The second part is the classifier; Multilayer Perceptron Network is designed for recognition purpose. It is used to train the train data set and classify the test data set that it is shown with its result box and sound. These data sets are composed of all Myanmar alphabets. For programming and simulation of this paper, MATLAB Programming Language is used for implementation. Myat Thida Tun"Myanmar Alphabet Recognition System Based on Artificial Neural Network" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-5 , August 2018, URL: http://www.ijtsrd.com/papers/ijtsrd17054.pdf http://www.ijtsrd.com/engineering/information-technology/17054/myanmar-alphabet-recognition-system-based-on-artificial-neural-network/myat-thida-tun