A shielded face recognition method and device based on feature transformation

Abstract

The embodiment of the invention provides a shielded face recognition method and device based on feature transformation, and the method comprises the steps: inputting a target face image into a presetconvolutional neural network model, and obtaining a feature map of the target face image from the last convolutional layer of the convolutional neural network model; Calculating a sub-pixel product ofthe feature map and a pre-obtained feature mask; And inputting the sub-pixel product into a feature layer of the convolutional neural network model, and outputting a feature for identification of thetarget face image. The embodiment of the invention provides a shielded face recognition method and device based on feature transformation. A feature transformation mode of adding a feature mask is adopted for an image of a shielded face, feature responses of common areas prone to being shielded of the face are abandoned, engineering implementation is easier, the calculation time is shorter, the network structure is simpler, and the recognition precision of the shielded face is improved.

Description

Technical field [0001] The embodiments of the present invention relate to the technical field of face recognition, and in particular to a method and device for occluded face recognition based on feature transformation. Background technique [0002] The application of face recognition is becoming more and more widespread, and the requirements for face recognition accuracy are getting higher and higher, especially when the face is partially occluded, the recognition accuracy is more important. [0003] In the prior art, the face recognition algorithm based on convolutional neural network is usually used for face recognition. However, the face recognition algorithm based on convolutional neural network largely depends on the quality of the data set, but in actual scenes Human faces have greater complexity in terms of occlusion and angle. It is also more difficult to manually label occluded face images, so most existing face recognition technologies have a serious problem in that the ...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the face recognition algorithm based on the convolutional neural network is usually used for face recognition. However, the face recognition algorithm based on the convolutional neural network largely depends on the quality of the data set, but in the actual scene Faces have greater complexity in terms of occlusions, angles, etc.

Manual labeling of occluded face pictures is also more difficult, so most existing face recognition technologies have the problem of serious decline in recognition accuracy for occluded face pictures

Most of the existing algorithms for improving the robustness of face occlusion use multi-network structures to train multiple face regions separately, and integrate the features of different regions of the face. However, these methods consume large computing resources and take longer to calculate. Disadvantages of more complex preprocessing of face images

Images