earticle

영어

Moving object tracking technique is to find the exact location of the target in the next frame, and feedback to a tracking system for tracking and to provide an important basis and foundation for the analysis and understanding of the video sequence. Face recognition refers to the method to extract somehow be able to describe the characteristics of each individual's personality. Using 2DPCA image feature extraction, feature dimension reduction is simpler and direct, so the calculation efficiency is relatively high, and it can greatly shorten the training time of the sample collection of images. This method is the first application the 2DPCA optimal representation of characteristics for the original sample matrix, and then apply FLDA optimal discriminate feature for the original sample. The paper proposes the method of moving target tracking based on 2DPCA and FLDA face recognition algorithm.