Image privacy recognition method, device, computer equipment and storage medium

Abstract

The present application relates to an image privacy identification method, device, computer equipment and storage medium. The method includes: acquiring an image to be identified; extracting residual matrixes of at least eight different directions of the image to be identified; determining a local residual pattern histogram of the image to be identified according to the residual matrix of at least eight different directions of the image to be identified; Obtain the Fisher score of the feature vector in the local residual pattern histogram of the image to be recognized, filter the feature vector in the local residual pattern histogram of the image to be recognized according to the Fisher score, and obtain the target feature vector of the image to be recognized; The feature vector is input into the trained image classification model, and whether the image to be recognized is a privacy image is identified according to the classification result of the image classification model. The method can efficiently and accurately judge whether there is private information hidden in the image, and the judgment process has low complexity and good robustness.

Description

technical field [0001] The present application relates to the technical field of information security, in particular to an image privacy identification method, device, computer equipment and storage medium. Background technique [0002] In recent years, with the development of computer technology and communication technology, the production and dissemination of information has become increasingly convenient. Maintaining personal privacy and improving the level of personal privacy protection are of great significance to society. There are some criminals who, through privacy hiding technology, embed users' private information in a specific carrier (such as audio, video, image, text, etc.) without being detected, in order to achieve the purpose of stealing the privacy of individuals, companies or governments , seriously impairing information security. [0003] Digital image privacy hiding technology can be understood as a technology that uses digital images as a carrier to rea...

AI Technical Summary

Problems solved by technology

At present, most of the anti-privacy hiding technologies for binary images extract features related to texture characteristics, morphological characteristics, and statistical characteristics from binary images, and then use classifiers to classify the features of binary images to judge Whether privacy-related information is hidden; however, the above classifiers tend to have high training complexity, poor robustness, and low accuracy of classification results

Images