In order to reduce the computational consumption of the training and the testing phases of\nvideo face recognition methods based on a global statistical method and a deep learning network,\na novel video face verification algorithm based on a three-patch local binary pattern (TPLBP) and\nthe 3D Siamese convolutional neural network is proposed in this paper. The proposed method\ntakes the TPLBP texture feature which has excellent performance in face analysis as the input of the\nnetwork. In order to extract the inter-frame information of the video, the texture feature maps of\nthe multi-frames are stacked, and then a shallow Siamese 3D convolutional neural network is used\nto realize dimension reduction. The similarity of high-level features of the video pair is solved by\nthe shallow Siamese 3D convolutional neural network, and then mapped to the interval of 0 to 1 by\nlinear transformation. The classification result can be obtained with the threshold of 0.5. Through an\nexperiment on the YouTube Face database, the proposed algorithm got higher accuracy with less\ncomputational consumption than baseline methods and deep learning methods.
Loading....