VIPPrint

VIPPrint数据集是由意大利锡耶纳大学信息工程与数学系创建的大规模数据集，专注于打印和扫描图像的合成人脸图像检测及其来源链接。该数据集包含41,600张图像，分为两部分：一部分用于打印机来源归属，包含1,600张图像；另一部分用于检测由生成对抗网络（GAN）生成的合成人脸图像，包含40,000张图像。VIPPrint数据集旨在推动数字图像取证领域的发展，特别是在打印文档的来源归属和合成图像检测方面，为算法开发和基准测试提供了丰富的资源。The VIPPrint dataset is a large-scale dataset developed by the Department of Information Engineering and Mathematics, University of Siena, Italy, focusing on the detection of synthetic facial images within printed and scanned images as well as their source attribution. Comprising 41,600 total images, the dataset is split into two subsets: one designed for printer source attribution, containing 1,600 images; the other for detecting synthetic facial images generated by Generative Adversarial Networks (GANs), with 40,000 images. The VIPPrint dataset aims to advance the field of digital image forensics, particularly in the domains of printed document source attribution and synthetic image detection, providing abundant resources for algorithm development and benchmark testing.

搜集汇总

背景与挑战

背景概述

VIPPrint数据集是一个由意大利锡耶纳大学创建的大规模数据集，包含41,600张图像，分为打印机来源归属（1,600张）和GAN生成合成人脸检测（40,000张）两部分。它专注于数字图像取证，旨在推动打印文档来源归属和合成图像检测的算法开发与基准测试。