Research And Implementation Of Face Detection Paralleled Algorithm

Face detection is a fundamental and important research theme in the topic of Pattern Recognition and Computer Vision and it has a broad application in many fields such as content-based image and video retrieval, video surveillance, human-computer interface and automatic face detection, etc.Face detection is the first phase of face anlysis, the problem refer to face detection is to determinate whether there are human faces in the image. If so, then locate the human faces in the image. AdaBoost algorithm is a fast face detection algorithm proposed by Viola et al in2001, it is a mile-stone in the field of object detection. This paper focuses on a face detection algorithm based on AdaBoost.AdaBoost theory can transform weak learning to strong learning, theoretically, if there are enough samples, and the training is absolutely adequate, the error rate of the classifiers that generated by AdaBoost algorithm is unlimited near zero. But, as the number of samples increases, the training time of AdaBoost algorithm becomes incredible long.To address this problem, this paper proposes a parallelization of AdaBoost face detection algorithm, by dividing the samples, making the training process can be performed in parallel, which signally accelerates the process of training samples, while training through each part of the sample obtained by a combination of weak classifiers, the error rate of the final strong classifier was also maintained at a desirable value. Then, combined with the characteristics of MapReduce, the improved algorithm is given a specific implementation. Finally, the experimental results verify the parallelization face detection algorithm can really improve the speed of training, and the speedup of the new algorithm for training time is superior to traditional parallelization.