Published Paper Details:

ABSTRACT This paper presents an automation of Kannada numerical handwritten word recognition system in that main challenge is recognition of handwritten words. The identification of Kannada handwritten words plays an important role because in Kannada script many words have a same size and same shape. The recognition of Kannada handwritten words is an important application in number plates, banks and other organizations. In this work we consider dataset contains 50 documents for each documents contains the 0-9 Kannada handwritten words 10 classes. Here we extracting the two different types of feature namely Gabor and LPBV (local binary pattern variance). The effect of each feature and their Combination in the words and signature classification is analyzed using the K-nearest neighbour classifiers. It is common to combine multiple categories of features into a single feature vector for the classification and also we apply the dimensionality reduction technique. Calculated Classification results based on feature extraction methods, varying the K values and randomly splitting the testing and training samples.