arXiv 2109.078022021-09-16cs.CVcs.AI

Compact Binary Fingerprint for Image Copy Re-Ranking

Department of CS and IT, University of Balochistan（信德大学计算机与信息技术系（注：原机构为University of Balochistan，直译为“俾路支斯坦大学”，其计算机与信息技术系为Department of CS and IT，此处按要求提取到大学级别，故完整机构为“俾路支斯坦大学计算机与信息技术系”））

Nazar Mohammad, Junaid Baber, Maheen Bakhtyar, Bilal Ahmed Chandio, Anwar Ali Sanjrani

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Image copy detection is challenging and appealing topic in computer vision and signal processing. Recent advancements in multimedia have made distribution of image across the global easy and fast: that leads to many other issues such as forgery and image copy retrieval. Local keypoint descriptors such as SIFT are used to represent the images, and based on those descriptors matching, images are matched and retrieved. Features are quantized so that searching/matching may be made feasible for large databases at the cost of accuracy loss. In this paper, we propose binary feature that is obtained by quantizing the SIFT into binary, and rank list is re-examined to remove the false positives. Experiments on challenging dataset shows the gain in accuracy and time.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

StyleSentinel：通过风格指纹实现可靠的艺术版权验证

StyleSentinel: Reliable Artistic Copyright Verification via Stylistic Fingerprints

StyleSentinel通过提取艺术作品的风格指纹，利用语义自重建、多层特征融合和最小包围超球面建模，将版权验证转化为单类学习任务，在单样本验证中超越现有方法。

2025-08-02cs.CV

基于深度 PatchMatch 与成对排序学习的图像复制-粘贴伪造检测

Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

Shenzhen University（深圳大学）；Ningbo University（宁波大学）；University of Macau（澳门大学）

提出一种端到端CMFD框架，结合深度跨尺度PatchMatch定位伪造区域并利用成对排序学习区分源与目标区域，显著提升了泛化能力和检测精度。

2024-04-26cs.CV

Learning to Disentangle GAN Fingerprint for Fake Image Attribution

Renmin University of China（中国人民大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）

Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake image attribution. Existing works on fake image attribution mainly rely on a direct classification framework. Without additional supervision, the extracted features could include many content-relevant components and generalize poorly. Meanwhile, how to obtain an interpretable GAN fingerprint to explain the decision remains an open question. Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Netw…

2021-06-16cs.CV

AI生成模型的因果指纹

Causal Fingerprints of AI Generative Models

Faculty of Data Science,City University of Macau（数据科学学院，澳门城市大学）；Nanjing University of Science and Technology（南京理工大学）；Zhejiang Cloudpeng Technology Co., Ltd.（浙江云鹏科技有限公司）

本文提出了一种基于因果解耦框架的方法，通过语义不变的潜在空间分离图像生成过程与模型痕迹，提升指纹的粒度，验证了因果关系在模型溯源和身份保护中的有效性。

2026-04-14cs.CV

U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting

Texas A&M University（得克萨斯农工大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

This paper studies the challenging problem of fingerprint image denoising and inpainting. To tackle the challenge of suppressing complicated artifacts (blur, brightness, contrast, elastic transformation, occlusion, scratch, resolution, rotation, and so on) while preserving fine textures, we develop a multi-scale convolutional network, termed U- Finger. Based on the domain expertise, we show that the usage of dilated convolutions as well as the removal of padding have important positive impacts on the final restoration performance, in addition to multi-scale cascaded feature modules. Our model …

2018-08-05cs.CV

A Watermarking Technique Using Discrete Curvelet Transform for Security of Multiple Biometric Features

C. U. Shah University（C. U. Shah 大学）；Atmiya Institute of Technology & Science（Atmiya 科技学院）

The robustness and security of the biometric watermarking approach can be improved by using a multiple watermarking. This multiple watermarking proposed for improving security of biometric features and data. When the imposter tries to create the spoofed biometric feature, the invisible biometric watermark features can provide appropriate protection to multimedia data. In this paper, a biometric watermarking technique with multiple biometric watermarks are proposed in which biometric features of fingerprint, face, iris and signature is embedded in the image. Before embedding, fingerprint, iris,…

2017-01-16cs.CRcs.CVcs.MM

更多相关论文收起更多论文

面向零样本模型归因的模型合成方法

Model Synthesis for Zero-Shot Model Attribution

Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Computer Science, Faculty of Engineering, University of Sydney（悉尼大学工程学院计算机科学学院）

针对现有生成模型归因方法无法适配未知模型的问题，提出基于模型合成技术的通用指纹提取器，仅用合成模型训练即可实现零样本归因，大幅提升未知模型的识别与验证准确率。

2025-01-17cs.CV

水印与指纹作为内容来源的软绑定：图像、音频和视频的开放许可基准

Watermarks and Fingerprints as Soft Bindings for Content Provenance: An Open-Licence Benchmark for Images, Audio and Video

Original Pictures Technologies, Inc.（Original Pictures Technologies 公司）

该基准在开放许可模型下比较水印与指纹两类内容来源软绑定方法，覆盖图像、音频和视频，发现PixelSeal和AudioSeal分别最优，并揭示指纹在图像副本检测上更有效，而水印在视频上更有效。

2026-10-06cs.CV

树轮水印：用于扩散图像且不可见且鲁棒的指纹

Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust

University of Maryland（马里兰大学）

本文提出Tree-Ring Watermarking技术，通过在扩散模型采样的初始噪声向量中嵌入傅里叶空间模式，实现不可见且对多种图像变换鲁棒的模型指纹，可即插即用于任意扩散模型且FID损失可忽略。

2023-07-04cs.CRcs.CVcs.LG

Rank Correlation Measure: A Representational Transformation for Biometric Template Protection

Despite a variety of theoretical-sound techniques have been proposed for biometric template protection, there is rarely practical solution that guarantees non-invertibility, cancellability, non-linkability and performance simultaneously. In this paper, a ranking-based representational transformation is proposed for fingerprint templates. The proposed method transforms a real-valued feature vector into index code such that the pairwise-order measure in the resultant codes are closely correlated with rank similarity measure. Such a ranking based technique offers two major merits: 1) Resilient to…

2016-07-23cs.CRcs.CV

Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing

Monash University Malaysia（莫纳什大学马来西亚校区）；Electronics and Telecommunications Research Institute（韩国电子通信研究院）；Yonsei University（延世大学）

In this paper, we propose a ranking based locality sensitive hashing inspired two-factor cancelable biometrics, dubbed "Index-of-Max" (IoM) hashing for biometric template protection. With externally generated random parameters, IoM hashing transforms a real-valued biometric feature vector into discrete index (max ranked) hashed code. We demonstrate two realizations from IoM hashing notion, namely Gaussian Random Projection based and Uniformly Random Permutation based hashing schemes. The discrete indices representation nature of IoM hashed codes enjoy serveral merits. Firstly, IoM hashing empo…

2017-09-17cs.CV

对抗攻击检测的神经指纹

Neural Fingerprints for Adversarial Attack Detection

The Hebrew University（希伯来大学）；Tel Aviv University（特拉维夫大学）

本文提出基于神经指纹的随机化检测器库，通过采样神经元子集和似然比检验，在白盒设置下实现对对抗样本的高效检测，在ImageNet上达到近乎完美的性能。

2024-11-07cs.CVcs.LGstat.AP

通过知识整合重新审视医学图像检索

Revisiting Medical Image Retrieval via Knowledge Consolidation

Bioengineering Department and Imperial-X, Imperial College（生物工程系和帝国理工学院）；Archimedes Unit, Athena Research Centre（阿基米德单元，阿提卡研究中心）；Hong Kong University of Science and Technology（香港科学大学）；Sun Yat-Sen University（孙中山大学）；CIMIM, Alan Turing Institute（CIMIM，艾伦·图灵研究所）；NIHR Manchester Biomedical Research Centre, University of Manchester（NIHR曼彻斯特生物医学研究中心，曼彻斯特大学）；National Heart and Lung Institute, Imperial College London（国家心脏和肺研究所，伦敦帝国学院）；Cardiovascular Research Centre, Royal Brompton Hospital（心血管研究中心，皇家布罗姆pton医院）；School of Biomedical Engineering and Imaging Sciences（生物医学工程与影像科学学院）

针对医学图像检索中瓶颈特征及OOD问题，提出整合层次特征与优化函数的方法，通过深度感知表示融合与结构感知对比哈希提升检索性能与安全性，显著优于现有方法。

2025-03-12cs.AIcs.CV