Remote identity authentication method based on single training sample face recognition

Abstract

The invention discloses a remote identity authentication method based on single training sample face recognition. A sub-feature measuring module is constructed by a moderate face sub-feature training sample, a P-dimensional sample data vector v is further generated, and a training result data set is formed by a machine learning algorithm. In a step 6), a certain picture of a single training sample is judged and an input picture to be recognized is recognized according to the machine learning algorithm and the training result data set, so that recognition rate is greatly increased, and a single training sample face recognition method has an industrial application prospect. In the step 6), the difference between sub-features refers to the distance between two sub-feature vectors in a distance space in topology meaning in general.

Description

technical field [0001] The invention relates to a single training sample face recognition method. Background technique [0002] Face recognition technology is the most representative and challenging important technical direction in the field of biometrics. Face recognition refers to the recognition of one or more faces from static or dynamic scenes based on known face sample databases using image processing and / or pattern recognition techniques. [0003] The current method of identity authentication based on the face recognition algorithm usually adopts the face recognition method of multiple training samples. It is necessary to do a large number of sampling work of multiple photos of a single person before the recognition, and the existing face database of a single person and a single photo in the country cannot be used; at the same time, because this method requires a large amount of collection work in the early stage, for a large number of The algorithm does not apply t...

AI Technical Summary

Problems solved by technology

[0006] "Identification method based on mobile phone camera combined with face recognition technology" (public number CN 101226591A) provides an identification method based on mobile phone camera combined with face recognition technology in the field of wireless network technology and pattern recognition. The invention patent The application emphasizes that the acquisition terminal is a mobile phone and the face recognition algorithm adopts principal component analysis (PCA) and linear discriminant analysis (LDA) to perform recognition training on the face data in the candidate data set, and then recognize the face area of ​​the input image , this method is difficult to obtain a higher recognition rate in terms of the current face recognition algorithm technology

Images