A fast face retrieval method and system

Abstract

The invention discloses a method and system for fast face retrieval. The method includes: obtaining a feature vector of an image, inputting the feature vector into an auto-encoder network, training and updating the self-encoder network to obtain the weight of a fully connected layer and the corresponding The bias item is used as a network parameter for binary hashing the feature vector, and the hash index library of the image is established through the network parameter to obtain the hash value of the image to be queried, and the face result is searched. In the present invention, by using a deep convolutional neural network for facial feature extraction, efficient facial feature expression can be obtained. At the same time, the self-encoding network is used to obtain the hash code, and a more compact binary expression is obtained based on the facial features. In addition, the present invention uses the Hamming distance of the hash code to calculate the image similarity, and the calculation amount is small and the retrieval speed can be accelerated.

Description

technical field [0001] The present invention relates to the field of deep learning and face image recognition, in particular to a fast face retrieval method and system, mainly based on convolutional neural network and self-encoding network binary hash. Background technique [0002] The face image database in the prior art includes many types, such as, FERET face database, CMU-PIE face database, YALE face database, MIT face database, ORL face database or the like. And the purpose of adopting the face image library is: in the face image library, retrieving similar face images has broad application prospects in face recognition directions such as monitoring and security. [0003] It is known that performing hash coding on the original image can effectively improve the speed of image retrieval. [0004] Such as in the prior art, Chinese patent application number: CN 201310087561.5 a kind of similar face retrieval method based on local sensitive hashing, discloses a kind of face...

AI Technical Summary

Problems solved by technology

[0005] The analysis shows that the shortcomings of this method are: the eyes, mouth and skin color features can not express the characteristics of the whole face well, and the local sensitive hashing method is a data-independent hashing method with strong randomness; To ensure better retrieval accuracy, the required number of coding bits is very long, and the retrieval efficiency is relatively low

[0007] The analysis shows that the disadvantage of this scheme is that the data of training images is less, and the global frequency features are not suitable for face recognition tasks.

Images