• Dr.V.V.Karthikeyan
• Mrs.S.Sujithra
• Miss.J.R.Beny

Artificial Neural Network has the ability to solve complex problem in this modern computing world. Image Processing with Artificial Neural Network (ANN) has found its application in identification and analysis of medical images, fingerprints, human images, speech recognition and in handwritten character recognition. In this paper Image processing with artificial neural network is used to recognition the offline handwritten characters. In offline character recognition, processing of various steps in series are carried out, such as pre-processing, feature extraction & finally classification using artificial neural network. In preprocessing we reduce the noise and increase the quality of the image and next we go for feature extraction. In extracting the feature we use novel method, bi-orthogonal wavelet function. The feature estimated using bi-orthogonal wavelet is saved for the each image in the training set. Thus the saved features are given as input to the Back Propagation Artificial Neural Network. It produces the output accurately based on the trained images. The method is used to recognize all the 24 English characters effectively.

Preprocessing, Feature extraction, recognition, Back Propagation, Artificial Neural Network(ANN)

"Algorithm for Offline Handwritten Character Recognition using Artificial Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 2, page no.230-234, February-2015, Available :http://www.jetir.org/papers/JETIR1502012.pdf

"Algorithm for Offline Handwritten Character Recognition using Artificial Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 2, page no. pp230-234, February-2015, Available at : http://www.jetir.org/papers/JETIR1502012.pdf