Internet video face recognition method based on deep learning

Abstract

The invention discloses an Internet video face recognition method based on deep learning, comprising the following steps: (a) marking face data, acquiring an image with a face from the Internet, marking a face location box and the name of the person, and establishing a face image library; and (b) using the face data marked in step (a) to train a convolutional neural network, wherein the input of the convolutional neural network is set as the face location box, and the output of the convolutional neural network is set as a name tag and the confidence level of the name tag. The beneficial effects are as follows: in face track analysis, first, the quality of each face image on the track is evaluated to discard low-quality face images and retain only high-quality images in order to guarantee the reliability of recognition, and then, statistical analysis is made on the tags of face recognition results of single frames on the track, face image quality filtering is carried out, and the face tags of the overall track are decided based on the statistical parameters of the tags, which can effectively avoid the influence of quality of video on the accuracy of recognition.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to an Internet video face recognition system based on deep learning. Background technique [0002] Face recognition is a technology that detects and locates a human face in a given image or video and identifies its identity. According to different data sources, face recognition technology can be divided into two categories: image-based and video-based. Due to the differences in the characteristics of video capture equipment and image capture equipment, especially the quality of captured images is usually higher than that of video, images have higher resolution and clarity, lower noise, etc., most people Face recognition methods are based on image recognition, and cannot be directly used in lower-quality video face recognition. [0003] With the development of network and big data, Internet video has become a larger source of video data, so face recognition based on Intern...

AI Technical Summary

Problems solved by technology

However, compared with traditional surveillance videos, Internet videos have different sources, formats, production methods, and quality. These features will greatly affect the accuracy of face recognition and pose new challenges to face recognition technology.

[0004] Applying the existing face recognition technology directly to Internet videos cannot achieve satisfactory recognition accuracy. Due to the huge amount of Internet video data, higher requirements are placed on the speed of face recognition algorithms. Many existing recognition methods cannot Adapt to new real-time processing application requirements

Images