Face key point detection method, system and device based on semantic alignment

Abstract

The invention belongs to the field of face recognition, and specifically relates to a method, system, and device for detecting key points of a face based on semantic alignment, aiming at improving the accuracy of key point detection of a face. After the face key point detection network, use the constructed training samples including the face image samples marked with key points and the standard Gaussian response map centered on the position of each key point, and use the probability model containing hidden variables as the maximum The goal of likelihood estimation is then optimized for the face key point detection network; the coordinates of face key points are predicted through the final optimized face key point detection network. The invention effectively overcomes the training shock problem caused by the randomness of labeling in the network training process, and improves the accuracy of face key point detection.

Description

technical field [0001] The invention belongs to the field of face recognition, and in particular relates to a method, system and device for detecting key points of a face based on semantic alignment. Background technique [0002] Face key points play an important role in face-based computer vision and pattern recognition applications, such as video surveillance and identity recognition systems. For most face applications, it is first necessary to accurately detect the key points of the face. [0003] In recent years, the mainstream face key point detection methods are mainly divided into two categories, one is the traditional method. One type is the method based on convolutional neural network. Traditional methods directly regress model parameters through manual image features. The representative method is cascade regression, and its fitting process can be summarized as the following formula: [0004] p k+1 =p k +Reg k (Fea(I,p k )) [0005] At the kth iteration, by...

AI Technical Summary

Problems solved by technology

However, there are a large number of weak semantic points in the key points of the face. These points are usually only required to be evenly distributed on the specified edge, such as the contour of the face, the eye socket, the bridge of the nose, etc., and there is no strict semantic position

Due to the low recognition of texture information around these weak semantic points, random errors inevitably exist in the manual labeling results, which leads to semantic inconsistencies in the labels of different samples.

Therefore, using manual calibration points to directly train the model will lead to a large number of invalid errors in the training process, so that the network fitting ability cannot be concentrated where it is really needed

So far, the impact of the randomness of the labeling of key points on model training has not been paid attention to

Images