Face tracking recognition technique based on video

Abstract

The invention relates to a face tracking recognition technique based on a video. The technique provided by the invention comprises the following steps: detecting the decoded video frame by frame; merging the number of faces and the position information of the faces into face activity position sequences; preprocessing the sequences; clustering the face activity position sequences into the face continuous activity region sequence of the same person by adopting a tracking algorithm; selecting an optimal face from each sequence by adopting face quality evaluation; carrying out normalization processing; carrying out Gabor conversion in a frequency region; carrying out histogram statistics on a converted image; solving a characteristic value; and finally, carrying out two-two subtraction on the characteristic values of the optimal faces in the different sequences and inputting the obtained statistic attribute characteristic value into a face recognizer for face matching, thereby recognizing the face activity tracking sequence of each person. Through the technique provided by the invention, the accuracy of sequence classification can be ensured, the times for characteristic extraction and face comparison are reduced, the problem that the faces cannot be tracked after being lost in the traditional face tracking is solved, and super real-time processing of a high-definition video is realized.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a bottom-up face tracking recognition method based on offline video. Background technique [0002] As a typical biometric identification technology, face recognition technology is favored by people for its naturalness, high reliability, and high degree of automation. Wide application prospects. For example, the public security industry needs to find and lock specific people's activity areas and activity periods in massive videos, or the mosaic processing of faces in program editing in the radio and television industry requires the use of face tracking and recognition technology in offline videos. [0003] In some video media libraries, if you want to find someone's activity period, the traditional method mainly relies on manual video browsing, which can imagine the heavy workload and low work efficiency. For example, in the non-linear editing of TV progr...

AI Technical Summary

Problems solved by technology

[0005] Another object of the present invention is to propose a video-based bottom-up face tracking and recognition method, which clusters the face activity positions into a sequence of human face activity areas, and solves the problem of traditional face tracking in discrete videos. The problem that it cannot be recovered after being lost, and the processing speed of high-definition video can reach super real-time

[0006] Another object of the present invention is to adopt a down-sampling method for large-format videos, and at the same time use block-based LBP operators (Block-BLP) to extract features and train face detectors to speed up detection and overcome the existing technology. The problem that face detection and recognition cannot realize real-time processing of high-definition video

[0007] Another object of the present invention is to overcome the problems of false detection and missed detection during face detection in the prior art by adopting a preprocessing program for eliminating noise face regions and connection breakpoints.

Images