Image tampering detection method based on full-resolution mixed attention mechanism

Abstract

The invention discloses an image tampering detection method based on a full-resolution mixed attention mechanism, and the method comprises the steps: obtaining a to-be-detected image, inputting the to-be-detected image into a pre-trained image tampering detection model based on the full-resolution mixed attention mechanism, and outputting a tampering detection result. The method has the advantages that the problem that the image resolution is reduced due to potential tampering of region texture features and loss of edge high-frequency features in an existing method is effectively solved, the direction of a network output vector is optimized, and the network training convergence speed is increased; a training method based on feedback ablation points is provided, and modular end-to-end training in a limited memory is achieved; the feedback of each module is combined to optimize and adjust parameters, and the reasoning test speed of the model is accelerated. The method has better accuracy, stronger robustness, faster training speed and smaller memory occupation in the aspect of detection tasks with multiple tampering types simultaneously, and has a very wide application prospect.

Description

technical field [0001] The invention relates to an image tampering detection method based on a full-resolution mixed attention mechanism, and belongs to the technical field of image processing. Background technique [0002] With the rapid development and use of multimedia acquisition equipment and artificial intelligence technology, people ushered in the era of multimedia information explosion. Digital image generation has become very easy. Ordinary people can use various image editing software and processing technologies to edit image content at any time. edit. These modifications for the purpose of beautification and entertainment will not bring adverse effects to our daily life. In some cases, maliciously tampered images will affect the public's judgment on objective things after being disseminated, and may even confuse the real ones, causing adverse effects on the country and society. In today's society, "seeing is believing" has become less and less credible. When peo...

AI Technical Summary

Problems solved by technology

Although better detection results can be achieved, the impact of local detection on global results is not considered

In practical applications, there is always a non-zero missed detection rate and false alarm rate. Once a local block is missed or falsely reported, it will cause a large deviation in the detection results of the entire image.

In addition, as mentioned above, the deep detection network has been constrained by computer computing power and memory, and there are problems of slow speed and large memory overhead.

Images