OBJECT RECOGNITION BASED ON LBP AND DISCRETE WAVELET TRANSFORM

Abstract

Automated object recognition from images plays a significant role in many computer vision systems such as content based image retrieval, navigation of robots and object manipulation processes. In this paper, Local Binary Patterns (LBP) and Discrete Wavelet Transform (DWT) techniques are analyzed for object recognition. The later technique helps us to extract the detailed information's of objects from its multi-scale representation. Using the extracted features, the recognition of objects can be done by the classifier known as the nearest neighbour classifier. A maximum of 98.03% average recognition accuracy is attained by the system with Columbia Object Image Library (COIL-100) objects while using the features of LBP and 6th level DWT energies.