View source for 20230116801. IMAGE AUTHENTICITY DETECTION METHOD AND DEVICE, COMPUTER DEVICE, AND STORAGE MEDIUM simplified abstract (Tencent Technology (Shenzhen) Company Limited)

=IMAGE AUTHENTICITY DETECTION METHOD AND DEVICE, COMPUTER DEVICE, AND STORAGE MEDIUM=


==Organization Name==

[[:Category:Tencent Technology (Shenzhen) Company Limited|Tencent Technology (Shenzhen) Company Limited]]


[[Category:Tencent Technology (Shenzhen) Company Limited]]

==Inventor(s)==

[[:Category:Taiping Yao of Shenzhen (CN)|Taiping Yao of Shenzhen (CN)]][[Category:Taiping Yao of Shenzhen (CN)]]

[[:Category:Xinyao Wang of Shenzhen (CN)|Xinyao Wang of Shenzhen (CN)]][[Category:Xinyao Wang of Shenzhen (CN)]]

[[:Category:Shouhong Ding of Shenzhen (CN)|Shouhong Ding of Shenzhen (CN)]][[Category:Shouhong Ding of Shenzhen (CN)]]

[[:Category:Jilin Li of Shenzhen (CN)|Jilin Li of Shenzhen (CN)]][[Category:Jilin Li of Shenzhen (CN)]]

[[:Category:Yunsheng Wu of Shenzhen (CN)|Yunsheng Wu of Shenzhen (CN)]][[Category:Yunsheng Wu of Shenzhen (CN)]]

==IMAGE AUTHENTICITY DETECTION METHOD AND DEVICE, COMPUTER DEVICE, AND STORAGE MEDIUM - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20230116801 titled 'IMAGE AUTHENTICITY DETECTION METHOD AND DEVICE, COMPUTER DEVICE, AND STORAGE MEDIUM

==Simplified Explanation==

The patent application describes a method for detecting the authenticity of an image using a generative adversarial network (GAN). Here is a simplified explanation of the abstract:

* The method starts by obtaining a target image that needs to be authenticated.
* The target image is then inputted into a generator within a GAN, which produces an artifact image that represents the difference between the target image and a real image.
* The generator is designed to output a prediction artifact image based on a sample image and generate a fitting image using this prediction artifact image.
* In the training stage, a discriminator is included in the GAN to determine the authenticity of the fitting image. This helps the generator learn the distinguishing features between a fake image and a real image.
* Finally, the authenticity of the target image is determined based on the artifact image.

Potential applications of this technology:

* Image forensics: This method can be used to detect manipulated or fake images, which is crucial in fields like journalism, law enforcement, and digital forensics.
* Content verification: It can be employed to verify the authenticity of images shared on social media platforms, preventing the spread of misinformation or misleading content.
* Copyright protection: The method can help identify unauthorized use or alteration of copyrighted images, aiding in the protection of intellectual property rights.

Problems solved by this technology:

* Image tampering detection: The method provides a reliable way to detect if an image has been manipulated or altered, helping to ensure the integrity and authenticity of visual content.
* Misinformation detection: By identifying fake or manipulated images, this technology can contribute to the fight against misinformation and fake news, promoting more accurate and trustworthy information dissemination.

Benefits of this technology:

* Improved image authentication: The use of a GAN allows for more accurate and robust detection of image authenticity compared to traditional methods.
* Automated process: The method can be automated, making it efficient and scalable for analyzing large volumes of images.
* Real-time detection: The technology can provide real-time detection of image authenticity, enabling quick decision-making and response in various applications.


==Original Abstract Submitted==

an image authenticity detection method includes: obtaining a target image; inputting the target image into a generator of a generative adversarial network, and outputting an artifact image corresponding to the target image through the generator, where the artifact image is used for representing a difference between the target image and a real image; the generator is configured to output a prediction artifact image corresponding to a sample image and generate a fitting image based on the prediction artifact image; and the generative adversarial network further comprises a discriminator in a training stage, and the discriminator is configured to discriminate the authenticity of the fitting image, to assist the generator to learn a difference feature between a false image and a real image; and determining an authenticity detection result of the target image based on the artifact image.



[[Category:G06V20/00]]
[[Category:G06V10/82]]
[[Category:G06V20/40]]
[[Category:G06V40/16]]
[[Category:G06V10/774]]
[[Category:G06V10/26]]
[[Category:G06V10/75]]