Kannada Handwritten Character Recognition Using Multi Feature Extraction Techniques

Aravinda.C.V, Dr. H. N.Prakash, Lavanya S

Abstract: In this paper, we have presented a method of feature extraction for handwritten character recognition. Handwritten character recognition is a complex task because of various writing styles of different individuals. Our Method yields good classification accuracy on handwritten characters, apart from complexity. Normalization and binarization are the pre-processing techniques used for getting accurate results of classification process in handwritten character recognition. To select a set of features is an important step for implementing a handwriting recognition system. In this work, we have extracted various features, namely-Hu's Invariant moments, Zernike moments, Zonal features and Fourier-Wavelet coefficients. The recognition process is carried out using Back Propagation Neural Network.

Keywords: Character Segmentation, Optical Character Recognition, Hand Written Character Recognition, Optical Hand Character Recognition, Neural Network Classifier

How to Cite?: Aravinda.C.V, Dr. H. N.Prakash, Lavanya S, "Kannada Handwritten Character Recognition Using Multi Feature Extraction Techniques", Volume 3 Issue 10, October 2014, International Journal of Science and Research (IJSR), Pages: 911-916, https://www.ijsr.net/getabstract.php?paperid=OCT14255, DOI: https://dx.doi.org/10.21275/OCT14255