Large-scale image dataset for perceptual hashing

With the rapid development of social media，multimedia information on the internet is updated at an exponential rate. Obtaining and transmitting digital images have become convenient，considerably increasing the risk of malicious tampering and forgery of images. Accordingly，increasing attention is given to image authentication and content protection. Many image authentication schemes have emerged recently，such as watermarking，the use of digital signatures，and perceptual image hashing （PIH）. PIH，also known as image abstract or image fingerprint，is an effective technique for image authentication that has attracted widespread research attention in recent years. The goal of PIH is to authenticate an image by compressing perceptual robust features into a compact hash sequence with a fixed length. However，a general dataset in this field is lacking，and the dataset constructed using other methods have many problems. On the one hand，the types of image content-preserving manipulations used in these datasets are few and the intensity of attacks is rela⁃ tively weak. On the other hand，the distinct images used in these datasets are extremely different from the images that must be authenticated，making it easy to distinguish them from each other. The convolutional neural networks （CNNs） trained by these datasets have poor generalizability and can hardly cope with the complex and diverse image editing operations in reality. This important factor has limited the development of the PIH field. On the basis of the preceding knowl⁃ edge，we propose a specialized dataset based on various manipulations in this study. This dataset can deal with complex image authentication scenarios. The proposed dataset is divided into three subsets：original，perceptual identical，and perceptual distinct images. The latter two correspond to the robustness and discrimination of PIH，respectively. Original images are selected from ImageNet1K，and each of them corresponds to one category. For identical images，we summarize the content-preserving manipulations commonly used in the field of PIH and group them into four major categories： geomet⁃ ric，enhancement，filter，and editing manipulations. Each major category is subdivided into different types， for a total of 35 single-image content-preserving manipulations. To ensure the diversity and reflect the randomness of image editing in reality，we set a threshold for each type of image content-preserving manipulation and let them randomly select the attack intensity within this range. In addition，we randomly combine multiple single-image content-preserving manipulations to form combination manipulations. Some combined manipulations in the test set have not been learned in the training set due to the randomness. This result is also in line with practical application scenarios，because many unlearned，combined image editing manipulations exist in reality. For perceptual distinct images， except for a portion of images unrelated to the original images，the other portions are selected from the same category that corresponds to each original image，increasing the difficulty of the dataset and improving the generalizability of the trained CNNs. Compared with previously adopted datasets，our dataset conforms more to the actual application scenario of the PIH task. Our dataset contains 1 200 original images，and each original image is subjected to 48 image content-preserving manipulations to generate 48 perceptual identical images. To balance the number of perceptual identical and distinct images，we also select 48 perceptual distinct images for each original image. Then，24 images are randomly selected among them，and the other 24 images are semantically similar to the original images. Therefore，each batch contains 1 original image，48 perceptual identical images，and 48 perceptual distinct images，for a total of 97 images. Our dataset has 1 200 original images or 116 400 images in total. The large amount of data ensures the effective training of CNNs.

随着社交媒体的迅猛发展，互联网上的多媒体信息正以指数级速率更新。获取与传输数字图像已变得极为便捷，这也大幅提升了图像被恶意篡改与伪造的风险。因此，图像认证与内容保护受到了越来越多的关注。近年来涌现出诸多图像认证方案，例如水印技术、数字签名应用以及感知图像哈希（Perceptual Image Hashing，PIH）。感知图像哈希，又称图像摘要或图像指纹，是一种用于图像认证的有效技术，近年来受到了广泛的研究关注。其目标是将感知鲁棒特征压缩为固定长度的紧凑哈希序列，以此实现图像认证。然而，该领域目前缺乏通用的数据集，且采用其他方法构建的数据集存在诸多问题：一方面，这些数据集所使用的图像内容保留操作类型有限，攻击强度相对较弱；另一方面，数据集中使用的差异化图像与实际待认证图像差异显著，极易被区分开来。基于此类数据集训练的卷积神经网络（Convolutional Neural Networks，CNN）泛化能力较差，难以应对现实中复杂多样的图像编辑操作，这一关键因素限制了感知图像哈希领域的发展。基于上述背景，本研究提出了一种面向各类操作的专用数据集，可应对复杂的图像认证场景。该数据集分为三个子集：原始图像、感知一致图像以及感知差异化图像，后两者分别对应感知图像哈希的鲁棒性与区分性要求。原始图像选自ImageNet1K，每幅图像对应一个类别。对于感知一致图像，我们梳理了感知图像哈希领域常用的内容保留操作，并将其划分为四大类别：几何变换、增强操作、滤波操作与编辑操作。每个大类又细分为不同的子类，总计35种单图像内容保留操作。为确保数据多样性并贴合现实中图像编辑的随机性，我们为每类图像内容保留操作设置了强度阈值，使其可在该范围内随机选取攻击强度。此外，我们还将多种单图像内容保留操作随机组合，形成复合操作。由于随机性的存在，测试集中的部分复合操作并未在训练集中出现，这也契合实际应用场景——现实中存在大量未被学习过的复合图像编辑操作。对于感知差异化图像，除了部分与原始图像无关的图像外，其余图像均选自与原始图像对应的同一类别，以此提升数据集难度，并增强训练所得卷积神经网络的泛化能力。与此前采用的数据集相比，本数据集更贴合感知图像哈希任务的实际应用场景。本数据集包含1200幅原始图像，每幅原始图像通过48种图像内容保留操作生成48幅感知一致图像。为平衡感知一致图像与差异化图像的数量，我们还为每幅原始图像选取了48幅感知差异化图像，其中随机选取24幅，剩余24幅与原始图像语义相似。因此，每一批次包含1幅原始图像、48幅感知一致图像以及48幅感知差异化图像，总计97幅图像。本数据集包含1200幅原始图像，总图像量达116400幅。海量的数据可为卷积神经网络的有效训练提供保障。

搜集汇总

背景与挑战

背景概述

该数据集是一个专为感知图像哈希（PIH）任务设计的大规模图像数据集，旨在提升图像认证模型的泛化能力。它基于ImageNet1K构建，包含原始图像、感知相同图像和感知不同图像三个子集，其中感知相同图像覆盖了35种单图像内容保持操作及随机组合操作，以模拟现实复杂编辑场景。数据集总计116,400张图像，规模大且设计多样，能有效支持卷积神经网络的训练。