Handwritten Kannada Numeral Recognition based on the Curvelets and Standard Deviation

Abstract

A feature extractor is generally used to characterize an object by making numerical measurements of the object. Features whose values are similar for objects belonging to the same class and dissimilar for objects in different classes are considered as good features. In this paper, an attempt is made to develop an algorithm for the recognition of handwritten Kannada numerals using fast discrete curvelet transform. Curvelet coefficients are obtained by applying the curvelet transform with different scales. Standard deviation is applied to the coefficients obtained and the result of this is used as the feature vector. A k-NN classifier is adopted for classification. The proposed algorithm is experimented on 1000 samples of numerals. The system is seen to deliver reasonable recognition accuracies for different scales with 90.5% being the highest for Scale 3. 

KanOCR: Conversion of Printed Kannada Document to Editable form using Convolutional Neural Networks

“…A method of identifying Kannada characters by feature extraction using Curvelet transform and standard deviation followed by a KNN classifier is described in [1]. The system works on offline handwritten Kannada character recognition.…”

A Comprehensive Survey on OCR Techniques for Kannada Script

“…Mamatha etal (2011) [13] have proposed an algorithm for recognition of Kannada vowels with different fonts and sizes.…”