Face spoofing detection method based on color analysis

Abstract

The invention relates to a face spoofing detection method based on color analysis, and belongs to the field of digital image processing and pattern recognition. The method comprises the following steps: an image preprocessing stage: cutting a face region into image blocks with the size of 128 * 128 from a video; a feature extraction stage: extracting features of the image through a local binary pattern and a color distance; and a classification stage: fusing the local binary pattern and the color distance feature vector, and then performing classification by using a support vector machine to obtain a result. According to the method, color information can be added on the basis of texture features, and the method is applied to face spoofing detection and can better help a system to learn color information between a real face and a counterfeit face. And meanwhile, compared with other methods for introducing color information, the method provided by the invention has the advantages of smaller calculation amount and higher calculation speed.

Description

technical field [0001] The invention belongs to the field of digital image processing and pattern recognition, relates to technologies such as local binary patterns, and in particular relates to a face deception detection method based on color analysis. Background technique [0002] With the widespread application of face recognition, more and more lawbreakers are trying to fake real faces by means of photos or videos to pass face recognition, causing serious losses to users. In order to ensure the security of face recognition, face spoofing detection technology is essential. [0003] Face spoofing attacks can be divided into three types according to the different attack vectors used by intruders, printing photo attacks, video attacks, and mask attacks. Due to its low cost and ease of use, attackers most often use printed photos or videos to carry out spoofing attacks. [0004] In order to deal with different face spoofing attacks, scholars have proposed a variety of spoof...

AI Technical Summary

Problems solved by technology

There are some differences in image quality between the real face and the counterfeit face. The theoretical basis is that the secondary imaging image will be better than the real person extracted under the same conditions after passing through two different shooting systems and a printing system or playback device. The quality of the face image is lower, and the image will also appear blurred

At the same time, secondary imaging images are more likely to be disturbed by video noise signals or irrelevant background information, which can cause other image quality problems

Images