Face image-based dazzle degree detection method and device, equipment and medium

Abstract

The invention relates to an artificial intelligence technology, and discloses a face image-based dazzle degree detection method. The method comprises the following steps: in response to a dazzle degree detection instruction of a face image, dazzling a target object to be authenticated by using a color sequence composed of multiple colors to obtain multiple dazzle sub-videos corresponding to the multiple colors; acquiring key frame images of a plurality of dazzle photon videos to obtain key frame images of different colors; determining a reference key frame image; performing frame difference on the key frame images with different colors and the reference key frame image, and combining obtained frame difference images; and inputting a fused image obtained by merging into a deep learning model to obtain a detection result that whether the dazzle degree is qualified after the target object to be authenticated is subjected to dazzling. In addition, the invention also relates to a block chain technology, and the detection result can be stored in a node of a block chain. The invention further provides a dazzle degree detection device based on the face image, electronic equipment and a medium. According to the invention, whether the dazzle degree reaches the dazzle standard can be accurately identified.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, and in particular to a method, device, electronic equipment and computer-readable storage medium for detecting the degree of glare based on a human face image. Background technique [0002] With the continuous development of technology, the recognition rate of face recognition technology based on mobile phones has been qualitatively improved. Compared with other biometric recognition technologies, face liveness detection technology has natural and unique advantages in practical applications. But at the same time, with the development of technology, the technical level of online black production is getting higher and higher, and examples of using fake faces to complete online face recognition are commonplace. Proving that "you are the real you" thus becomes a crucial issue in various businesses such as banking. [0003] Among the many living body detection algorithms in th...

AI Technical Summary

Problems solved by technology

[0003] Among the many living body detection algorithms in the prior art, detection by glare has outstanding performance in terms of pass rate and anti-attack ability. However, the degree of glare in different environments is not the same, which will lead to the detection effect of glare. It is also different. For example, under different light intensities, the accuracy of glare detection is inconsistent. In the case of strong light, the accuracy of glare detection is low.

Images