Model training method and device, electronic equipment and computer readable storage medium

Abstract

The embodiment of the invention relates to the technical field of deep learning, and discloses a model training method and device, electronic equipment and a computer readable storage medium. The model training method comprises the following steps: acquiring a face attitude angle coarse label of a training sample according to coordinates of key points pre-marked by the training sample, wherein the training sample is a two-dimensional face image, the key points comprise a left eye center, a right eye center, a nose tip, a left mouth corner and a right mouth corner, and the face attitude angle coarse label comprises a pitch angle and a yaw angle; obtaining joint probability distribution of face attitude angles of the training sample according to the face attitude angle coarse label and a preset candidate attitude angle set; and training a preset deep learning network according to the training sample, the joint probability distribution and a preset loss function to obtain a face attitude angle estimation model. According to the model training method provided by the invention, the calculated amount in the training process is very small, the time required for training is relatively short, and a stable and reliable face attitude angle estimation model can be quickly obtained.

Description

Technical field [0001] The present application relates to the field of deep learning techniques, and in particular, to a model training method, device, electronic device, and computer readable storage medium. Background technique [0002] With the continuous development of computer vision technology, face recognition technology has been mature, and is widely used in all aspects of border prevention inspection, mobile payment, intelligent access control, and remote medical and other people's lives, based on deep learning face recognition technology, in ideal In the real environment, it has been able to achieve very high recognition accuracy, but under some scenes of reality, face recognition technology will be affected by face gesture, different face postures, such as pitch, left and right rotation, will cause a certain The deletion of some facial information, which results in a decline in the accuracy of the face recognition, so estimates to the human face attitude is an importan...

AI Technical Summary

Problems solved by technology

[0002]With the continuous development of computer vision technology, face recognition technology has become increasingly mature and widely used in border inspection, mobile payment, smart access control, telemedicine, etc. In all aspects, the face recognition technology based on deep learning can achieve very high recognition accuracy in an ideal implementation environment, but in some real scenarios, the face recognition technology will be affected by the attitude angle of the face. Different face poses, such as pitching and left-right rotation, will cause some facial information to be missing, which will lead to a decrease in the accuracy of face recognition. Therefore, estimating the face pose angle is important to ensure the accuracy of face recognition technology. one ring

[0003]However, whether it is based on the two-dimensional information of the face image, that is, estimating the face pose angle based on the relative position information of several key points of the face, or using the depth camera Collect face images to obtain 3D information, and then estimate the face pose angle based on the relationship between the 3D information and the standard reference face, or estimate the face pose angle based on the pre-trained deep learning network, and estimate the face pose angle The process is time-consuming and labor-intensive, the speed is relatively slow, and the accuracy of the estimated face pose angle is not high

Images