Multi-feature and multi-model living body face recognition method

Abstract

The invention provides a multi-feature and multi-model living body face recognition method. The method comprises the steps of obtaining a to-be-recognized RGB face image; decomposing the whole area ofthe RGB face image into a plurality of local areas, and segmenting to obtain an RGB image associated with each local area; performing feature transformation on the RGB image of the local area to obtain a corresponding HSV image, combining the RGB image and the HSV image to form input image information, and outputting the input image information; respectively inputting the input image informationinto each neural network model in the corresponding classification network model for identification so as to respectively obtain model features output by each neural network model corresponding to thelocal area; and inputting model features output by all neural network models in all classification network models into a feature output layer in a unified manner to form a feature output matrix, andinputting the feature output matrix into the fusion feature network model for recognition to output a living body face recognition result of the RGB face image. The method has the beneficial effect ofimproving the accuracy of living body face recognition.

Description

technical field [0001] The invention relates to the technical field of image analysis, in particular to a multi-feature and multi-model live face recognition method. Background technique [0002] At present, face recognition has been widely used in various fields, especially in scenarios such as access control payment. If the liveness detection effect is not good, the following dangerous situations will occur, such as dangerous people entering the park by mistake, or stealing other people's accounts, etc., so liveness detection is very important in such scenarios. [0003] In the prior art, for the problem of living body, RGB+NIR near-infrared binocular living body detection, or RGB+structured light binocular living body detection algorithm are mostly used; however, the above methods require hardware matching, resulting in high manufacturing costs, and cannot satisfy Most live detection scenarios; currently, a single classification model can also be used to directly classif...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, for the problem of living body, RGB+NIR near-infrared binocular living body detection, or RGB+structured light binocular living body detection algorithm are mostly used; however, the above-mentioned methods require hardware matching, so the manufacturing cost is high, and it cannot satisfy Most live detection scenarios; currently, a single classification model can be used to directly classify living or non-living objects. However, it is difficult to adapt to all scenarios using the above-mentioned single classification model, without generalization, and the accuracy of the model is not high.

Images