嘘~ 正在从服务器偷取页面 . . .

人脸相关


⚠️ 以下所有内容总结都来自于 大语言模型的能力,如有错误,仅供参考,谨慎使用
🔴 请注意:千万不要用于严肃的学术场景,只能用于论文阅读前的初筛!
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ,还请您给我们一些鼓励!⭐️ HuggingFace免费体验

2025-11-05 更新

Leveraging Large-Scale Face Datasets for Deep Periocular Recognition via Ocular Cropping

Authors:Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio, Josef Bigun

We focus on ocular biometrics, specifically the periocular region (the area around the eye), which offers high discrimination and minimal acquisition constraints. We evaluate three Convolutional Neural Network architectures of varying depth and complexity to assess their effectiveness for periocular recognition. The networks are trained on 1,907,572 ocular crops extracted from the large-scale VGGFace2 database. This significantly contrasts with existing works, which typically rely on small-scale periocular datasets for training having only a few thousand images. Experiments are conducted with ocular images from VGGFace2-Pose, a subset of VGGFace2 containing in-the-wild face images, and the UFPR-Periocular database, which consists of selfies captured via mobile devices with user guidance on the screen. Due to the uncontrolled conditions of VGGFace2, the Equal Error Rates (EERs) obtained with ocular crops range from 9-15%, noticeably higher than the 3-6% EERs achieved using full-face images. In contrast, UFPR-Periocular yields significantly better performance (EERs of 1-2%), thanks to higher image quality and more consistent acquisition protocols. To the best of our knowledge, these are the lowest reported EERs on the UFPR dataset to date.

本文专注于眼部生物识别技术,特别是眼部周围区域(眼睛周围的区域),该区域具有高鉴别力和最小的采集限制。我们评估了三种不同深度和复杂度的卷积神经网络架构,以评估它们在眼部识别方面的有效性。这些网络在从大规模VGGFace2数据库中提取的1907572个眼部区域上进行训练。这与现有工作形成鲜明对比,现有工作通常依赖于仅包含几千张图像的小规模眼部数据集进行训练。实验是在VGGFace2的子集VGGFace2-Pose的面部图像以及UFPR-Periocular数据库上进行的,UFPR-Periocular数据库由用户指导在屏幕上通过移动设备拍摄的自拍照组成。由于VGGFace2的非控制条件,使用眼部区域获得的等误率(EERs)范围在9%\textasciitilde{}15%之间,明显高于使用全脸图像获得的3%\textasciitilde{}6%的EERs。相反,UFPR-Periocular由于图像质量更高和更一致的采集协议而表现更好(EERs为1%\textasciitilde{}2%),据我们所知,这是迄今为止在UFPR数据集上报告的最低EERs。

论文及项目相关链接

PDF Published at IWAIPR 2025 conference

Summary

本文主要探讨了眼部生物识别技术,特别是围绕眼睛的区域(眼周生物识别)。通过评估三种不同深度和复杂程度的卷积神经网络架构,研究其在眼周识别中的有效性。训练数据来自大规模的VGGFace2数据库中的1907572个眼部图像片段,这与现有研究形成鲜明对比,现有研究通常只依赖包含数千张图片的小规模眼周数据集进行训练。实验采用包含自然场景面部图像的VGGFace2-Pose子集和通过移动设备拍摄的自拍图像组成的UFPR-Periocular数据库。由于VGGFace2的不受控条件,眼部图像片段的等误报率(EERs)在9-15%之间,明显高于使用全脸图像的3-6%的EERs。相比之下,UFPR-Periocular由于图像质量更高、采集协议更一致,表现优异,实现了迄今为止最低的EERs(1-2%)。

Key Takeaways

  1. 研究关注眼部生物识别技术中的眼周区域。
  2. 使用卷积神经网络进行深度学习和分析。
  3. 训练数据来自大规模的VGGFace2数据库中的眼部图像片段。
  4. 对比现有研究,本研究使用的训练数据量更大。
  5. 实验采用包含自然场景面部图像的VGGFace2-Pose子集和自拍图像组成的UFPR-Periocular数据库进行测试。
  6. 在VGGFace2数据集上,眼部图像的等误报率较高(9-15%)。

Cool Papers

点此查看论文截图

DArFace: Deformation Aware Robustness for Low Quality Face Recognition

Authors:Sadaf Gulshad, Abdullah Aldahlawi

Facial recognition systems have achieved remarkable success by leveraging deep neural networks, advanced loss functions, and large-scale datasets. However, their performance often deteriorates in real-world scenarios involving low-quality facial images. Such degradations, common in surveillance footage or standoff imaging include low resolution, motion blur, and various distortions, resulting in a substantial domain gap from the high-quality data typically used during training. While existing approaches attempt to address robustness by modifying network architectures or modeling global spatial transformations, they frequently overlook local, non-rigid deformations that are inherently present in real-world settings. In this work, we introduce \textbf{DArFace}, a \textbf{D}eformation-\textbf{A}ware \textbf{r}obust \textbf{Face} recognition framework that enhances robustness to such degradations without requiring paired high- and low-quality training samples. Our method adversarially integrates both global transformations (e.g., rotation, translation) and local elastic deformations during training to simulate realistic low-quality conditions. Moreover, we introduce a contrastive objective to enforce identity consistency across different deformed views. Extensive evaluations on low-quality benchmarks including TinyFace, IJB-B, and IJB-C demonstrate that DArFace surpasses state-of-the-art methods, with significant gains attributed to the inclusion of local deformation modeling.

人脸识别系统通过深度神经网络、先进的损失函数和大规模数据集取得了显著的成功。然而,在处理涉及低质量面部图像的现实场景时,它们的性能往往会下降。这种退化在监控录像或远距离成像中很常见,包括低分辨率、运动模糊和各种失真,与训练时通常使用的高质量数据之间存在明显的领域差距。尽管现有方法试图通过修改网络架构或建模全局空间变换来提高稳健性,但它们经常忽略现实环境中固有的局部非刚性变形。在这项工作中,我们介绍了\textbf{DArFace},一个\textbf{D}变形感知\textbf{A}稳健\textbf{r}人脸识别框架,它提高了对这种退化的稳健性,而无需配对的高质量和低质量训练样本。我们的方法通过对抗性地整合全局变换(例如旋转、平移)和局部弹性变形来进行训练,以模拟现实生活中的低质量条件。此外,我们引入了一个对比目标,以在不同变形的视图中强制执行身份一致性。在低质量基准测试上的广泛评估,包括TinyFace、IJB-B和IJB-C,证明DArFace超越了最先进的方法,其显著收益归因于局部变形建模的加入。

论文及项目相关链接

PDF

Summary
人脸识别系统通过深度神经网络、先进的损失函数和大规模数据集取得了显著的成功。但在涉及低质量人脸图像的实际情况中,其性能往往会下降。为解决这一问题,本文提出了DArFace框架,该框架增强了低质量图像的人脸识别鲁棒性,无需配对高低质量训练样本。通过模拟真实低质量条件,对抗性地结合了全局变换和局部弹性变形,并引入对比目标来强化不同变形视图之间的身份一致性。在低质量基准测试中,DArFace超越了最先进的方法,其中显著的提升归功于局部变形建模的引入。

Key Takeaways

  1. 人脸识别系统在实际应用中面临低质量图像的挑战。
  2. DArFace框架旨在增强对低质量图像的人脸识别鲁棒性。
  3. DArFace结合了全局变换和局部弹性变形模拟真实低质量条件。
  4. DArFace引入了对比目标来强化不同变形视图之间的身份一致性。
  5. DArFace在多个低质量基准测试中表现超越现有最先进的方法。
  6. 显著的性能提升归功于局部变形建模的引入。

Cool Papers

点此查看论文截图

Face Spoofing Detection using Deep Learning

Authors: Najeebullah, Maaz Salman, Zar Nawab Khan Swati

Digital image spoofing has emerged as a significant security threat in biometric authentication systems, particularly those relying on facial recognition. This study evaluates the performance of three vision based models, MobileNetV2, ResNET50, and Vision Transformer, ViT, for spoof detection in image classification, utilizing a dataset of 150,986 images divided into training , 140,002, testing, 10,984, and validation ,39,574, sets. Spoof detection is critical for enhancing the security of image recognition systems, and this research compares the models effectiveness through accuracy, precision, recall, and F1 score metrics. Results reveal that MobileNetV2 outperforms other architectures on the test dataset, achieving an accuracy of 91.59%, precision of 91.72%, recall of 91.59%, and F1 score of 91.58%, compared to ViT 86.54%, 88.28%, 86.54%, and 86.39%, respectively. On the validation dataset, MobileNetV2, and ViT excel, with MobileNetV2 slightly ahead at 97.17% accuracy versus ViT 96.36%. MobileNetV2 demonstrates faster convergence during training and superior generalization to unseen data, despite both models showing signs of overfitting. These findings highlight MobileNetV2 balanced performance and robustness, making it the preferred choice for spoof detection applications where reliability on new data is essential. The study underscores the importance of model selection in security sensitive contexts and suggests MobileNetV2 as a practical solution for real world deployment.

数字图像欺骗已经成为生物识别系统(尤其是依赖面部识别的系统)中的重大安全威胁。本研究评估了三种基于视觉的模型(MobileNetV2、ResNET50和Vision Transformer,即ViT)在图像分类中的欺骗检测性能,利用一组包含150986张图像的数据集进行训练(14002张图像用于训练,10984张图像用于测试,以及39574张图像用于验证)。欺骗检测对于提高图像识别系统的安全性至关重要,本研究通过准确性、精确度、召回率和F1分数等指标比较了模型的有效性。结果表明,在测试数据集上,MobileNetV2优于其他架构,实现了91.59%的准确率、91.72%的精确度、91.59%的召回率和91.58%的F1分数,相比之下,ViT的相应指标分别为86.54%、88.28%、86.54%和86.39%。在验证数据集上,MobileNetV2和ViT表现优异,其中MobileNetV2以97.17%的准确率略微领先于ViT的96.36%。尽管两者都显示出过拟合的迹象,但MobileNetV2在训练过程中表现出更快的收敛速度和对新数据的更好泛化能力。这些发现凸显了MobileNetV2的平衡性能稳健性,使其成为在需要新数据可靠性的欺骗检测应用中的首选。该研究强调了安全敏感环境中模型选择的重要性,并建议将MobileNetV2作为实际部署的实际解决方案。

论文及项目相关链接

PDF The author’s school has a conflict of interest regarding the submission of this article prior to his graduation thesis submission

摘要

数字图像欺骗已成为生物识别系统的重要安全威胁,特别是在依赖面部识别的系统中。本研究评估了三种基于视觉的模型MobileNetV2、ResNET50和Vision Transformer(ViT)在图像分类中的欺骗检测性能,使用了由训练集、测试集和验证集组成的包含超过百万张图片的数据集。欺骗检测对于提高图像识别系统的安全性至关重要,本研究通过准确度、精确度、召回率和F1分数等指标比较了模型的有效性。结果显示,在测试数据集上,MobileNetV2优于其他架构,准确度达91.59%,精确度达91.72%,召回率达91.59%,F1分数达91.58%,而ViT相应指标分别为86.54%、88.28%、86.54%和86.39%。在验证数据集上,MobileNetV2和ViT表现优异,其中MobileNetV2以微弱优势领先,准确度达97.17%,而ViT准确度为96.36%。尽管两者均显示过拟合的迹象,但MobileNetV2在训练过程中收敛更快,对新数据的泛化能力更强。这些发现凸显了MobileNetV2平衡的性能和稳健性,使其成为欺骗检测应用的首选方案,尤其是那些需要在新数据上可靠运行的应用场景。研究强调了安全敏感环境中模型选择的重要性,并建议将MobileNetV2作为实际应用部署的实用解决方案。

关键见解

  1. 数字图像欺骗对生物识别系统构成重大威胁,特别是在依赖面部识别的系统中。
  2. 评估了三种模型MobileNetV2、ResNET50和Vision Transformer在图像欺骗检测方面的性能表现。
  3. 在测试数据集上,MobileNetV2展现出最佳的准确性、精确度、召回率和F1分数等性能指标。
  4. 在验证数据集上,MobileNetV2同样表现优异,且相较于其他模型具有更快的收敛速度和更强的泛化能力。
  5. MobileNetV2被推荐为实际部署的实用解决方案,尤其是在需要在新数据上可靠运行的场景中。
  6. 研究强调了模型选择在安全敏感环境中的重要性。

Cool Papers

点此查看论文截图


文章作者: Kedreamix
版权声明: 本博客所有文章除特別声明外,均采用 CC BY 4.0 许可协议。转载请注明来源 Kedreamix !
 上一篇
无监督/半监督/对比学习 无监督/半监督/对比学习
无监督/半监督/对比学习 方向最新论文已更新,请持续关注 Update in 2025-11-05 C-LEAD Contrastive Learning for Enhanced Adversarial Defense
下一篇 
检测/分割/跟踪 检测/分割/跟踪
检测/分割/跟踪 方向最新论文已更新,请持续关注 Update in 2025-11-05 Overcoming Prompts Pool Confusion via Parameterized Prompt for Incremental Object Detection
  目录