Authors: N. Sandhya; R. Krishnan; D.R. Ramesh Babu; N. Bhaskara Rao
Addresses: Department of CSE, Faculty – Dayananda Sagar College of Engineering, Bangalore, 560078, India ' Department of CSE, Dayananda Sagar College of Engineering, Bangalore, 560037, India ' Department of CSE, Faculty – Dayananda Sagar College of Engineering, Bangalore, 560078, India ' Department of CSE, Faculty – Dayananda Sagar College of Engineering, Bangalore, 560078, India
Abstract: Recognition of historical printed degraded Kannada characters is not solved completely and remains as a challenge to the researchers still. In this paper, a scale for measuring degradation of a character is proposed. Further, the degradation is characterised to high, medium and low based on this scale, and use it to study the efficiency of the character restoration technique designed. A new approach, fit discriminant analysis (FDA) for recognition is proposed and compares its recognition accuracy with the existing techniques support vector machines (SVM) and Fisher linear discriminant (FLD) analysis. Through extensive experimentation it is established that rebuilding of characters improves the recognition accuracy of learning-based approaches SVM, FDA, and FLD significantly. Further, it is established that the proposed approach FDA gives the best recognition accuracy for historical printed degraded documents. It is also proved that training-testing set applying the proposed degradation measure is required for better recognition accuracy.
Keywords: degraded characters; support vector machines; SVM; Fisher linear discriminant analysis; broken characters.
International Journal of Advanced Intelligence Paradigms, 2019 Vol.14 No.1/2, pp.14 - 29
Received: 16 Jun 2016
Accepted: 01 Oct 2016
Published online: 14 Oct 2019 *