A face detection method

Abstract

The invention discloses a face detection method, which comprises the following steps: 1. The input image is first scaled to different sizes according to a certain ratio through the image pyramid, and then sequentially passed through the first-level network in the form of a sliding window, and roughly predicted The coordinates of the face, the confidence of the face and the orientation of the face, after that, filter out most of the negative samples according to the confidence ranking, and send the remaining image blocks to the second-level network; 2. The second-level network Further filter out non-face samples and return more accurate position coordinates, and give the prediction result of the face orientation; 3. The angle arbitration mechanism will combine the prediction results of the first two networks to make the final rotation angle of each sample. Arbitration; 4. Each image block is corrected according to the arbitration result of the angle arbitration mechanism, and then sent to the third-level network for fine adjustment to predict the position of the key point. The invention realizes the alignment of the human face with any rotation angle to the position of the standard human face.

Description

technical field [0001] The invention relates to the technical field of face detection in the field of computer vision, in particular to a face detection method. Background technique [0002] Face detection has a wide range of applications in the fields of identity authentication, security, media and entertainment. The problem of face detection originated from face recognition and is a key step in realizing face recognition. The diversity of aspects such as , illumination, and scale brings great challenges to the detection of human faces and their key points. In the past ten years, a large number of methods have emerged in the field of computer vision to improve the ability of machines to detect human faces. The traditional Face detection methods can be divided into methods based on geometric features, methods based on skin color model and methods based on statistical theory according to the realization mechanism. Among them, the method based on geometric features mainly uses...

AI Technical Summary

Problems solved by technology

[0004] The paper by Sun Yi et al. (Sun Y, Wang X, Tang X. Deep Convolutional Network Cascade for Facial Point Detection[C] / / Computer Vision and Pattern Recognition, 2013 IEEE Conference on.IEEE, 2013.) introduced deep learning into human face for the first time Key point detection task, TCDCN (Zhang Z, Luo P, Loy C C, et al. Facial Landmark Detection by DeepMulti-task Learning [C] / / European Conference on Computer Vision. Springer, Cham, 2014.) Utilization and face key The expression, gender and other attributes closely related to points improve the robustness of key point detection, but these methods are separated from face detection, which makes such methods have a greater dependence on the detection results of the previous step. HyperFace (Ranjan R, Patel V M, Chellappa R.HyperFace:A Deep Multi-task LearningFramework for Face Detection,Landmark Localization,Pose Estimation,and GenderRecognition[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2018,PP(99):1-1.) Will More attribute labels are added to the training task, and the accuracy of key point regression is improved through multi-task learning. However, too many learning tasks bring a greater amount of calculation and more running time. For tasks with high real-time requirements, this method obviously has many limitations

Images