Abstract: In the proposed Telugu character recognition technique, the given Telugu handwritten document is processed by normalizing the document and removing the noise. Then, skew detection and correction process is carried out by using the bilinear interpolation method to get more accurate result. Thus, the de-skewed documents text lines and characters are segmented by exploiting the Adaptive Histogram Equalization (AHE). In the next stage, the features of the segmented characters are extracted with the help of the Zoning Method. In Zoning Method, an adaptive fuzzy membership function will be developed by the AGA (Adaptive Genetic Algorithm). By using AGA in Zoning Method the features are extracted from the segmented characters and that extracted features is given to the FFBNN (Feed Forward Back Propagation Neural Network) for accomplishing the training process. During testing, more number of handwritten segmented Telugu characters will be given to the well trained FFBNN to check whether the input character is recognized or not. Thus, our proposed method has given more accurate recognition results by using our proposed adaptive fuzzy membership function with AGA Method. The proposed method performance is evaluated by getting more number of handwritten Telugu documents and compared with the GA-FFBNN and FFBNN.
P.K. Venkateswar Lal, Ande Prasad and M. Venkat Rao, 2015. Adaptive Fuzzy Membership Functions with AGA Techniques in Telugu Character Recognition. Asian Journal of Information Technology, 14: 11-22.