Image forgery multi-type detection method and system based on visual big language model

Through the multimodal feature fusion and context reasoning of the visual large language model, the problems of single modal limitations and insufficient multi-type detection capabilities in image forgery detection are solved, and high-precision detection and positioning of copy-paste and splicing forgery are realized, and detailed forgery text descriptions are output.

CN120388380APending Publication Date: 2025-07-29GUANGDONG VOCATIONAL COLLEGE OF POST & TELECOM
0 Cites 7 Cited by

Patent Information

Application Number
CN202510343921.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-22
Publication Date
2025-07-29

AI Technical Summary

Technical Problem

In the image forgery detection, the existing technology has problems such as single modal limitations, insufficient multi-type detection capabilities and low positioning accuracy of forgery areas, and it is difficult to effectively integrate multimodal information and simultaneously detect copy-paste and splicing forgery.

Method used

The visual large language model is adopted, through multimodal feature fusion and context reasoning, the visual and language features are extracted using pre-trained convolutional neural networks and language models, combined with multimodal alignment technology, high-precision detection and positioning of copy-paste and splicing forgery, and the forged text description is output.

Benefits of technology

It realizes high-precision detection and positioning of copy-paste and splicing forgery, improves the generalization ability of the model in complex scenarios, provides detailed forgery text descriptions, and enhances the understanding and utilization of multimodal information.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses an image counterfeiting multi-type detection method and system based on a visual large language model, and belongs to the technical field of image processing and computer vision. The method comprises the following steps of: preprocessing a data set containing normal, copy and paste forged and spliced forged images, extracting visual and language features by utilizing a pre-training model, and realizing feature fusion by adopting a multi-modal alignment technology. Whether an image is forged or not is judged through a classification task, a forged area is positioned through a segmentation task, and meanwhile a forged text description is output through a text generation module. The loss function is optimized in combination with classification, segmentation, comparison and text cross entropy loss. And adopting an end-to-end training and course learning strategy training model, and outputting a forgery probability, a regional mask and text description during reasoning. According to the method, multiple counterfeit types can be processed at the same time, high-precision positioning is achieved, multi-modal information is effectively fused, and detailed counterfeit text description can be provided.
Need to check novelty before this filing date? Find Prior Art