Face recognition method based on uncertainty quantization probability convolutional neural network

Abstract

The invention relates to a face recognition method based on an uncertainty quantization probability convolutional neural network. The method comprises a training stage and an identification stage. Theprobabilistic convolutional neural network is trained through samples with known categories. The extraction of face features is realized by a learning process of a probability convolutional neural network. The description of the face features is represented by the connection weight; testing the trained probability convolutional neural network by using a training sample, and determining a classification threshold. A to-be-identified sample is input into the probability convolutional neural network. An output vector of the probability convolutional neural network is calculated. A maximum component is compared with a classification threshold value to give an identification result. Uncertainty quantitative analysis is made on the identification result, and a mean value and variance estimationof the identification result are provided. The probability convolutional neural network system is adopted. The explicit feature extraction process is avoided through the difference extraction layer and the feature mapping layer. The feature which greatly contributes to the construction of the sample space is implicitly obtained from the sample. Compared with the prior art, the recognition rate and the anti-interference performance are higher.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a face recognition method based on uncertainty quantization probability convolutional neural network. Background technique [0002] Face recognition technology is a technology that uses computers to analyze face images, extract effective feature information, and identify personal identities. It first judges whether there is a face in the image? If it exists, the position and size information of each face is further determined. Based on this information, the potential pattern features in each face are further extracted, and compared with the faces in the known face database, so as to identify the category information of each face. Among them, the process of judging whether there is a face in an image is face detection, and the process of comparing the extracted image with the known face database is face recognition. [0003] The current face recognition method ...

AI Technical Summary

Problems solved by technology

[0012] 1. There is not much difference between different individuals. All faces have similar structures, and even the structural shapes of human face organs are very similar; such characteristics are beneficial for using faces for positioning, but for using faces to distinguish the human individual is disadvantageous

[0013] 2. The shape of the human face is very unstable. People can produce many expressions through changes in the face, and at different viewing angles, the visual images of the human face are also very different. In addition, face recognition is also affected by lighting conditions (such as daytime and Influenced by many factors such as night, indoor and outdoor environments), many coverings on the face, age, shooting posture angle, etc.

[0014] It can be known from the above that the existing face recognition technology is affected by human organs and facial expressions, which increases the interference factors of face recognition, making face recognition low in efficiency and with many interference factors.

Images