Informatics Publishing Limited

H. R. Mamatha ¹, K. Srikanta Murthy ², Priya Vishwanath ¹, T. S. Savitha ¹, A. S. Sahana ¹, S. Suma Shankari ¹

Affiliations
1 Department of ISE, PES Institute of Technology, Bangalore, IN
2 Department of CSE, PES School of Engineering, Bangalore, IN

Abstract

The automatic classification of patterns is a broad area of research in the machine learning area. The aim of pattern classification is the allocation of a certain input to a specific class in a predefined set of classes. Examples of pattern classification tasks are automatic identification of diseases based on a set of symptoms, optical character recognition, automatic document classification, speech recognition, etc.,. In classification problems, the classification rates depend significantly on similarity measures. Classification depends largely on distance or similarity as neighbors are different depending on similarity measures. Therefore it is important to choose a suitable similarity measure. In this paper an Evaluation of four different similarity measures such as Euclidean, Chebyshev, Manhattan and cosine for recognition of Handwritten Kannada numerals have been done. Here, image fusion technique has been used where extracted features of the several images corresponding to each handwritten numeral are fused to generate patterns, which are stored in 8x8 matrices, irrespective of the size of images. Zonal based feature extraction algorithm is being used to extract the features of Handwritten Kannada numerals. The numerals to be recognized are matched using nearest neighbor classifier with different similarity measures against each pattern and the best match pattern is considered as the recognized numeral. Results show that Euclidean distance measure outperforms other similarity measures in terms of recognition accuracy.

Keywords

Similarity Measures, OCR, Handwritten Kannada Numerals, Image Fusion, Zonal Based Feature Extraction, Nearest Neighbour Classifier.

Full Text

     

S. Karthik ¹, H. R. Mamatha ², K. Srikanta Murthy ³

Affiliations
1 Department of IS&E, PES School of Engineering, Bangalore, IN
2 Department of IS&E, PES Institute of Technology, Bangalore, IN
3 Department of CS&E, PES School of Engineering, Bangalore, IN

Abstract

Optical Character Recognition (OCR) is one of the important field in image processing and pattern recognition domain. Many practical applications uses OCR with high accuracy. The accuracy of the Optical Character Recognition system depends on the quality of the features extracted and the effectiveness of the classifier. Here we are proposing a novel method to recognize the printed kannada vowels. Kannada script has large number of characters having similar shapes and also the complexity is font dependent, which means the same characters in a class, may vary in structure for different fonts. Hence a method, which makes use of image zoning and the Run Length Count techniques to extract the features have been proposed. The methodology uses Naive Bayes classifier, K-Nearest Neighbor classifier for classification. The method experimented on a dataset, which consists of samples from 69 different fonts, and a maximum of 97.44% recognition accuracy is achieved.

Keywords

Optical Character Recognition, Naive Bayes Classifier, K-Nearest Neighbor Classifier, Zoning, Run Length Count.

Full Text