Human face identification method based on human face characteristic data mining and device

Abstract

The invention relates to a human face identification method based on a human face characteristic data mining technology and a device. Through the special system structure design of a human face registration module, a human face identification module and a system updating module and a specific algorithm, effective intra-class registration human face characteristic information volume is increased, thus the method and the device adapt to the change of human face pose and facial expression. Through automatic system updating, identification rejection rate caused by the fact that an environment and a human face change with time is reduced. For the characteristic differences between types of intra-class human faces, the respective classification threshold is mined. The delay rate caused by the fact that the same classification threshold is used and intra-class human face differences are ignored and the identification rejection rate are reduced. The identification efficiency of a system is improved.

Description

technical field [0001] The invention discloses a face recognition technology, in particular a face recognition method and device based on face feature data mining technology, belonging to the field of face recognition. Background technique [0002] Face recognition technology is a biometric identification technology that uses facial feature information for identity identification. It has the advantages of non-contact acquisition, concealed operation, convenient and fast, powerful post-event tracking ability, strong interactivity and low image acquisition cost. , Widely used in information security, video surveillance, criminal detection, public security, social entertainment and other fields. The existing face recognition system generally includes two working modes, namely face registration mode and face recognition mode, which usually adopts 6 steps, namely: face detection, face key point positioning, face shape and texture normalization transformation, feature ext...

AI Technical Summary

Problems solved by technology

[0009] The test results of the existing technology in the AR library are significantly better than the recognition results in the YALE library, indicating that the existing technology is more suitable for the situation where there is a single expression or lighting, but the recognition rate is low for the situation where there are both expressions and lighting changes , which is also a common phenomenon that the existing face recognition products often have low recognition efficiency when expressions and lighting exist at the same time

At the same time, multiple iterations of the existing technology are likely to cause model overfitting. After the test face corresponding to the registered face feature database changes, the formation rate and misrecognition rate increase, lack of generalization ability, and the existing The increase in recognition time and decrease in efficiency brought about by multiple iterations of the technology is not conducive to the practical application of the technology

Images