Face Recognition Using Radon & Wavelet Transform
Gayatri K. Bhole, Mayur Dilip Jakhete · 2015
This paper presents a new pattern recognition technique for face recognition based on the combination of Radon and wavelet transforms, which is variant to variations in facial expression, and illumination. It is very difficult to identify images or user at changing expressions. In this paper, designed of a system is used to identify the user having variant facial expression and illumination with the higher recognition rates and better accuracy. It is also robust to zero mean white noise. The technique computes Radon projections in different orientations and captures the directional features of face images. Further, the wavelet transform applied on Radon space provides multi resolution features of the facial images. Being the line integral, Radon transform improves the low-frequency components that are useful in face recognition. For classification, the nearest neighbor classifier has been used. Experimental results using ATT databases containing 50 images show the superiority of the proposed method with some of the existing popular algorithms.