The development of the "Document Image Tampering Detection Standard" led by the China Academy of Information and Communications Technology has started

Global Network Technology Comprehensive ReportOn June 15th, the China Academy of Information and Communications (hereinafter referred to as the "China Academy of Information and Communications") recently launched the development of the "Document Image Tampering Detection Standard" (hereinafter referred to as the "Standard"), with the aim of providing reliable guarantees for the security of document image content and assisting in the construction of the new era AI security system.This standard is led by the Chinese Academy of Information Technology and Communications, and jointly prepared by Shanghai Hehe Information Technology Co

Global Network Technology Comprehensive ReportOn June 15th, the China Academy of Information and Communications (hereinafter referred to as the "China Academy of Information and Communications") recently launched the development of the "Document Image Tampering Detection Standard" (hereinafter referred to as the "Standard"), with the aim of providing reliable guarantees for the security of document image content and assisting in the construction of the new era AI security system.

This standard is led by the Chinese Academy of Information Technology and Communications, and jointly prepared by Shanghai Hehe Information Technology Co., Ltd., China Association of Graphic Graphics, University of Science and Technology of China and other scientific and technological innovation enterprises and well-known academic institutions.

As the leading party, China Academy of Information and Communications stated that the "Standards" will be based on the current industry situation, focusing on industry focus issues such as "fine-grained" visual difference forgery image recognition, generative image recognition, and document image integrity protection, in order to gather industry consensus and provide effective guidance for the industry.

According to the introduction of the joint information involved in the preparation of the Standard, previously, the technical research objects of image tamper detection mainly focused on natural scene images. For the tampered qualification certificates, documents, chat screenshots and other document images, traditional detection systems are often difficult to determine tampering and locate the content of the modification.

This is because, on the one hand, the diversity of tampering methods in real scenes and the subtle visual traces of tampering pose challenges to tamper detection schemes; On the other hand, the complexity of document layout and the diversity of text content have also become obstacles in the process of image content detection and recognition. In addition, traditional image tamper detection methods still have room for improvement in terms of detection coverage, accuracy, and security when faced with global cropping, color matching, and combination forgery techniques.

In response, Hehe Information stated that in order to achieve precise detection of text tampering traces, deep learning based image tampering detection technology and related systems have been developed, which can detect various forms of tampering, intelligently capture the subtle traces left by images during the tampering process, and display the tampering location of the image area in the form of a heat map. The relevant technology has been applied in industries such as banking and insurance.

Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.(Email:[email protected])