Individual identity identification method based on deep learning

Abstract

An individual identity identification method based on deep learning comprises the steps of: utilizing individual data with marked identities to carry out pairing, establishing positive and negative training samples, utilizing the training samples to train an established dual-channel convolution neural network model until the neural network model is convergent, and obtaining neural network model parameters after the training; and utilizing the trained neural network model and related parameters to carry out matching between individual images to be identified and registered individual images, determining the identities of the individual images to be identified according to the magnitude ordering of matching similarities, and outputting a result. According to the invention, characteristic extraction and distance measuring are unified in one one-to-end network, and the global optimization of the whole body is realized; a deep network is utilized to learn characteristic and measuring matrixes, the generalization is higher, and the individual identity identification problem under complex large-scale data is overcome; in addition, the real-time speed is reached, and the practical value is higher.

Description

technical field [0001] The present invention relates to the field of video surveillance and pattern recognition, in particular to an individual identification method based on deep learning, which mainly solves the problem of individual identification based on different viewing angles or under cameras. Background technique [0002] At present, most of the individual identification problems based on different viewing angles or cameras follow the traditional solution framework, that is, first perform feature extraction on two individual pictures under different viewing angles, and then establish a feature measurement matrix through sample learning. The features are matched, the distance is calculated, and then the distance is used to judge whether the two individual pictures belong to the same person. The effectiveness of the framework depends on the strength of the extracted feature representation and metric matrix. So far, the artificially designed features and metric matric...

AI Technical Summary

Problems solved by technology

So far, the artificially designed features and metric matrices have poor generalization and are difficult to solve the problem of complex and large-scale data.

Images