Face recognition method and system based on spatio-temporal feature fusion and sample attention enhancement

A spatio-temporal feature, face recognition technology, applied in the field of computer vision, can solve the problems of video time and space randomness, no perception of the recognized object or target, and reduced recognition accuracy, so as to improve the recognition accuracy.
CN113239866AActive Publication Date: 2021-08-10XIDIAN UNIV
6 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Applications(China)
Current Assignee / Owner
XIDIAN UNIV
Publication Date
2021-08-10

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a face recognition method and system based on spatio-temporal feature fusion and sample attention enhancement. The method comprises the following steps: obtaining a specific target face sequence in a video through face detection, and scoring the specific target face sequence; performing time feature extraction on the face sequence by using a time sequence processing algorithm ConvGRU; selecting an image with the highest score from the face sequence as a key frame; sending into a Resnet50 network to extract three feature maps with different depths, and calculating by using a spatial feature fusion algorithm ASFF to obtain spatial features; and finally, splicing the obtained time features and the space features in channel dimensions, sending the spliced features to a global average pooling layer and a full connection layer, and training the model by using a proposed ADAM-Softmax loss function. The ADAM-Softmax loss function can adaptively enhance the attention of samples with large intra-class difference, so that the model can achieve high recognition accuracy while rapid convergence is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of computer vision, and in particular relates to a face recognition method and system based on spatio-temporal feature fusion and sample attention enhancement. Background technique

[0002] In recent years, with the rapid development of deep learning technology, face recognition technology based on static images has made great progress. This is due to the constantly updated advanced neural network architecture and the unremitting efforts of scientific researchers in the theory of feature extraction. The progress of face recognition technology based on static images has also promoted the successful implementation of related application products. Relying on the powerful feature extraction capability of CNN network and the real-time performance of lightweight neural network, face recognition has been used in campus security, life services, etc. The field has achieved relatively good results.

[0003] However,...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More