Balanced sample set construction method and device, duplicated image recognition method and device, equipment and medium

Abstract

The invention discloses a balanced sample set construction method and device, a duplicated image recognition method and device, equipment and a medium. The method comprises the steps of obtaining an unbalanced duplicated sample set and a preset target balanced sample number; inputting the unbalanced copying sample set into a DVAE-GAN network model in the balanced sample set construction model fortraining; recording the converged DVAE-GAN network model as a trained DVAE-GAN network model until the total loss value of the DVAE-GAN network model reaches a preset convergence condition; if the target equalization sample number is greater than the positive sample number and the negative sample number at the same time, randomly generating a positive copy simulation sample and a negative copy simulation sample by the trained DVAE-GAN network model; and obtaining a balanced copy sample set for training a copy recognition model. According to the invention, the sufficient number of balanced copying samples are generated through the balanced sample set construction model to be trained by the copying recognition model, the time for collecting the copying samples can be shortened, and the recognition accuracy and the hit rate of the copying recognition model are improved.

Description

technical field [0001] The present invention relates to the field of image classification, and in particular to a method, device, computer equipment and storage medium for constructing a balanced sample set and recognizing a duplicate image. Background technique [0002] With the development of the credit society, more and more application scenarios (such as: application scenarios involving finance, insurance, and security) need to verify user identities through document recognition and face recognition. With the improvement of data photography technology, methods for criminals to verify user identities through re-photographed images emerge in endlessly, and the verification process becomes more and more difficult to verify. In the existing technology, it is mainly through automatic identification of re-photographed images for verification, which requires a lot of Remake images and normal images are used to train the remake recognition model, so as to improve the accuracy an...

AI Technical Summary

Problems solved by technology

With the improvement of data photography technology, methods for criminals to verify user identities through re-photographed images emerge in endlessly, and the verification process becomes more and more difficult to verify. In the existing technology, it is mainly through automatic identification of re-photographed images for verification, which requires a lot of Remake images and normal images are used to train the remake recognition model, so as to improve the accuracy and hit rate of the remake recognition model for remake image recognition, but the number of images required for training the remake recognition model is very large, and it is usually difficult to obtain Such a large number of training images, and the ratio of remake images obtained in actual application scenarios to normal images is very unbalanced, such as one in a million. Therefore, the accuracy and hit rate of the remake recognition model after training are not high, resulting in no recognition during the identity verification process. If remake images are identified, there will be security issues for user information

Images