April2015 Issue Vol.5 No.4
Ph.D Research Scholar & Associate Professor, Department of Computer Science,Navarasam College of Arts & Science for Women, Erode, Tamil Nadu,India
Research Supervisor & Head
Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India.
Abstract: Today, image processing penetrates into various fields, but till it is struggling in identification and recognition issues. Speech recognition is developed into a very active research area specializing on how to extract and recognize within images. The text based Speech identification and recognition is widely used biometric application for security and identification concern. The various methods have been proposed for speech identification and recognition each method has advantages and drawbacks. The complexity in identification and recognition, other issues affects performance of existing system makes insufficient. In this paper presents speech identification and recognition on full image and on Row suggest of an image. In each of the methods, effect of different quantity of coefficients of transformed picture is determined. The Row and Column Feature (RCF) vector are calculated separately and stored.The feature is generated and matching is done by Euclidean distance classification is used to measure a distance between diagnosed speech. The experimental result shows that RCF provides better recognition rate when compared with the existing methods.
Keywords: DCT, WALSH, HAAR, RCF.