Hybrid parallel approach based on wavelet transformation and principle component analysis for solving face recognition problem

Face recognition is the most complex approach for identifying people in biometrics. Other biometric approaches, such as iris recognition, finger print, etc, for human recognition require close contact with the person. Traditional algorithm for face recognition are concerned with both accuracy and timing. Timing issue is more critical when dealing with real time images, thus, attention was directed toward parallelization of such algorithms. Recent computer graphics hardware contains extremely powerful graphics processing units (GPU) which can be used to accelerate automatic face recognition systems. GPUs are reasonably priced units designed to perform a number of tasks on enormous amounts of data. Utilizing the parallel computing power of the GPU can reduce time of many general purpose applications, and real time systems. This paper design a hybrid approach to face recognition system based on GPU implementation using wavelet transformation and principle component analysis (PCA).