Infrared image conversion method and device, living body detection method, device and readable storage medium

Abstract

The invention discloses an infrared image conversion method, a living body detection method, a device, and a readable storage medium. The method comprises the steps: obtaining a visible light image and a near-infrared image; carrying out CycleGAN model training according to the visible light image and the near-infrared image; wherein generators of the CycleGAN model are two functions which are approximately reversible to each other, and the two generators share parameters in the training process; and inputting a target visible light image to the trained CycleGAN model to obtain a converted near-infrared image, and preferably inputting the near-infrared image to the living body detection model to obtain a judgment result. According to the technical scheme, the visible light image is directly converted into the near-infrared image, and the living body detection is carried out, so that the living body detection accuracy is effectively improved, and the attack of the prosthesis can be effectively resisted. A visible light image is converted into a near-infrared image by using a reversible network structure, parameter sharing is performed on a forward generator and a reverse generator by using an additive coupling technology, and the quality of the generated near-infrared image is superior to that of the near-infrared image generated by using a traditional CycleGAN method.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to an infrared image conversion method, a living body detection method, a device, and a readable storage medium. Background technique [0002] With the development of image recognition technology, face recognition plays an important role in security monitoring, face payment, access control and other fields. As the technology becomes more familiar to the public, concerns about the security of facial recognition have become more prevalent, drawing research from both academia and industry. Face recognition systems are vulnerable to some attacks. For example, a person may use photos, videos or masks of other identities to attack the face recognition system for illegal benefits. Therefore, it is necessary to carry out live detection, that is, to judge whether the image collected by the camera is a real person, which is very important to the security of the face recognition syst...

AI Technical Summary

Problems solved by technology

[0004] The existing infrared image acquisition methods are mainly divided into two categories: the first is to directly use near-infrared cameras to collect near-infrared images, but near-infrared equipment is relatively expensive, and a large number of available images in real application scenarios are collected from visible light environment, such as surveillance video and ID card photos; the second method is based on image transformation, which uses artificial intelligence technology to convert visible light images into near-infrared images. The CycleGAN method, although this method overcomes the problem of unpaired training data, can also convert visible light images into near-infrared images, but because the two generators are separated during the training process, the converted images inevitably have quality problems , and the additional image conversion module also reduces the inference speed of the model to a certain extent

Images