Comparison of Gabor Wavelet and Neural Network-based Face Detection Algorithms

P.V. Bazanov, D.Y. Buryak (Russia), W.J. Mun (Korea), A.B. Murynin (Russia), and H.K. Yang (Korea)


Face detection, pattern recognition, computer vision, Gabor wavelets, artificial neural network.


We propose a comparative research analysis of two major approaches to 2D face detection problem – local feature invariant approach and appearance-based approach. The local feature invariant approach is represented by the algorithm based on Gabor wavelets and geometry estimation. The appearance-based approach is represented by SNoW neural networks. The experimental evaluation of both algorithms has been performed on the testing database. The algorithms comparison has been carried out by using several measures calculated during evaluation procedure. As a result of comparison we present the integrated method for 2D detection that has been implemented in the 3D face recognition system.

Important Links:

Go Back