False face detection method and device, electronic equipment and computer readable storage medium

Abstract

The invention relates to the image processing technology, and discloses a false face detection method comprising the following steps: carrying out frequency domain conversion and high pass filtering on an original face image, thus obtaining an initial face image, and calculating to obtain a first false face probability value; carrying out face detection interception on the original face image to obtain a face frame, carrying out expansion or reduction operation on the face frame by utilizing a preset proportion to obtain a face interception image set, carrying out fine-grained classification processing, obtaining a fine-grained probability value set, and carrying out fusion to obtain a second false face probability value; and performing weighted fusion on the two probability values to obtain a human face detection probability value, comparing the human face detection probability value with a preset detection threshold, and judging whether the original human face image is a judgment result of a false face. The invention also relates to a blockchain technology, and the judgment result and the like can be stored in the blockchain node. The invention further discloses a false face detection device, electronic equipment and a storage medium. The invention can solve the problems that an existing detection method is insufficient in detection precision and long in detection algorithm time consumption.

Description

Technical field [0001] The present invention relates to the field of image processing, and more particularly to a fake face detection method, apparatus, electronic device, and computer readable storage medium. Background technique [0002] With face recognition, the technology of face unlocking is widely used in major fields, and academia and industrial commissions are increasingly paying attention to human face anti-counterfeiting and human body detection. At present, a large number of black products have attacked all facial recognition systems through high-end technologies, and the reality of face synthesis is getting higher and higher, and the success rate of attack is greatly improved. In particular, the matching living body detection is not strong in front of the fake face synthesis. [0003] At present, the facial synthesis detection method is to calculate the gradient amplitude and texture contrast of the human face edge, and the judgment of face synthesis by chromaticity,...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a false face detection method, device, electronic equipment and computer-readable storage medium, the main purpose of which is to solve the problem that the features extracted by the existing detection methods cannot well express the characteristics of synthetic faces

Images