Living body detection method

Abstract

The invention provides a living body detection method, which relates to the field of face recognition. The invention solves the problem that the safety of the recognition mode of the living face and the non-living face under the single color space is not high, the key points of the technical scheme are as follows: for each sample in the training set, the color acceleration robust features of the images in HSV color space and YCbCr color space are calculated respectively, and the two color acceleration robust features of each sample in the training set are fused into a set of color accelerationrobust features by vector fusion; the color-accelerated robust feature set of each sample in the training set is input into the Gaussian mixture model, and the FV coding vectors of each sample in thetraining set are calculated by the Gaussian mixture model; the FV coding vectors of each sample in the training set are normalized and converted into the format required by the classifier, and then sent to the classifier for training to train the model, and the remaining samples are used as a test set to adjust the relevant parameters of the model.

Description

technical field [0001] The invention relates to face recognition technology, in particular to the technology of how to more safely recognize living human faces in an access control system or an advertising machine. Background technique [0002] In recent years, key breakthroughs have taken place in the field of computer vision. Face recognition is a non-contact technology, which is visualized and conforms to people's thinking habits, and can be widely used in business, security and other fields. At present, face recognition has gradually become a hot research field. [0003] The United States is the first country to start face recognition technology, and it is also the first country to apply this technology. The level of its face recognition technology has been at the forefront of the world. The FBI launched their new generation of electronic identification system in 2014, with a total investment of more than 1 billion US dollars. It is used to lock criminal suspects by mo...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a living body detection method to solve the problem that the current living body detection method only uses a single color space to recognize living and non-living human faces and will be broken, and the problem of low security