Parallel computing of WaveCluster algorithm for face recognition application

There have been widely applied many research related to face recognition system. The system is commonly used for video surveillance, human and computer interaction, robot navigation, and etc. Along with the utilization of the system, it leads to the need for a faster system response, such as robot navigation or application for public safety. A number of classification algorithms have been applied to face recognition system, but it still has a problem in terms of computing time. In this system, computing time of the classification or feature extraction is an important thing for further concern. Classification algorithm that is suitable for very large databases and efficient in time complexity is WaveCluster. WaveCluster based on wavelet transform able to analyze function at different resolution. To enhance system ability as a real-time system, WaveCluster will be present to be parallel process and implemented on GPU using CUDA. CUDA is a parallel computing architecture that can manage high-performance parallel computing on GPU with large memory bandwidth. The parallelization of WaveCluster algorithm on GPU using CUDA is expected to speed-up the process computing time compared to serial process on CPU. In addition, the system is intended to improve level of accuracy in recognition process of facial images.