Multi-scale living body detection method and system based on deep learning

Abstract

The invention discloses a multi-scale living body detection method based on deep learning. The method comprises the following steps: step 1, inputting a picture, and extracting a multi-scale image; step 2, extracting multi-scale features of the multi-scale image: extracting the multi-scale features of the multi-scale image by using a deep learning model to obtain face image information features, environment information features and behavior information features; step 3, acquiring multi-scale fusion features: performing feature fusion on the extracted multi-scale features by adopting differentconstraints to obtain the multi-scale fusion features; and step 4, inputting the multi-scale fusion features to the classification network, outputting a living body score, and obtaining a living bodyinspection result according to a threshold value. Compared with an existing living body detection method based on a single face area, the method provided by the invention has better scene adaptabilityand higher detection accuracy in a poor imaging environment.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a multi-scale living body detection method and system based on deep learning. Background technique [0002] Biometrics, especially face recognition, has been a research hotspot in the field of computer vision for a long time. With the development of deep learning and the improvement of hardware computing equipment, face recognition technology is widely used in various fields, such as mobile phone face unlocking, access control machine face attendance and online face recognition payment. At present, face recognition technology has potential security risks of identity information being stolen. Criminals can use forged live face information for identity verification, and after passing identity verification, they can carry out illegal activities such as embezzling property and endangering public safety. Face recognition applications require a liveness detection...

AI Technical Summary

Problems solved by technology

At present, there are many RGB image liveness detection algorithms based on traditional vision and deep learning. However, a single liveness detection algorithm based on face information is easily affected by the environment and equipment, such as lighting environment and equipment imaging quality. In some poor environments Under this condition, it is difficult for the algorithm to distinguish between living and non-living

Images