Computerized Object Recognition System Using Undecimated Wavelet Transform and Nearest Neighbour Classifier

Australian Journal of Basic and Applied Sciences, Vol. 10(2), Pages: 85-88, 2016

4 Pages Posted: 9 Jul 2017

See all articles by P. Elakkiya

P. Elakkiya

PRIST University - Department of Computer Science and Engineering

S. Audithan

PRIST University - Department of Computer Science and Engineering

K. Raja

Bharathiar University

G. Kannan

PRIST University, Department of Computer Science and Engineering, Students

Date Written: January 8, 2016

Abstract

Object recognition is one of the main functions in human visual system. The recognition of categories of objects in images has become a central topic in computer vision. However it is a technically challenging and most important problem in computer vision due to various illuminations, size, and colour. In this paper, a robust and automated objects recognition system is presented using Undecimated Wavelet Transform (UWT) and K-Nearest Neighbour (KNN) classifier. To extract features from the given images, UWT decomposition is taken place at a predefined level of decomposition. Then, energy features are computed from all UWT sub-bands. To facilitate the recognition process, KNN classifier is employed. In order to assess the performance of the proposed approach, experiments are carried out using COIL database images. It provides satisfactory recognition accuracy of over 80% at 6th level of UWT decomposition.

Keywords: Object Recognition, Undecimated Wavelet Transform K-Nearest Neighbor Classifier and Energy

Suggested Citation

Elakkiya, P. and Audithan, S. and Raja, K. and Kannan, G., Computerized Object Recognition System Using Undecimated Wavelet Transform and Nearest Neighbour Classifier (January 8, 2016). Australian Journal of Basic and Applied Sciences, Vol. 10(2), Pages: 85-88, 2016. Available at SSRN: https://ssrn.com/abstract=2791804

P. Elakkiya (Contact Author)

PRIST University - Department of Computer Science and Engineering ( email )

Thanjavur, Tamil Nadu 613403
India

S. Audithan

PRIST University - Department of Computer Science and Engineering

Thanjavur, Tamil Nadu 613403
India

K. Raja

Bharathiar University

Coimbatore
India

G. Kannan

PRIST University, Department of Computer Science and Engineering, Students

Thanjavur
India

Register to save articles to
your library

Register

Paper statistics

Downloads
6
Abstract Views
60
PlumX Metrics