[论文解读] Towards Efficient Unconstrained Palmprint Recognition via Deep Distillation Hashing

Huikai Shao, Dexing Zhong+1 more|arXiv (Cornell University)|Apr 7, 2020

Biometric Identification and Security参考文献 69被引用 8

一句话总结

本文提出了一种轻量级、高效的无约束环境下的掌纹识别方法——深度蒸馏哈希（DDH），该方法利用深度神经网络和知识蒸馏技术。通过将掌纹图像转换为紧凑的二进制编码，并利用新型蒸馏损失函数训练小型学生网络，DDH在包含超过20,000张智能手机拍摄图像的无约束基准数据集上实现了最先进（SOTA）的准确率，且Equal Error Rate（EER）降低了高达3.11%。

ABSTRACT

Deep palmprint recognition has become an emerging issue with great potential for personal authentication on handheld and wearable consumer devices. Previous studies of palmprint recognition are mainly based on constrained datasets collected by dedicated devices in controlled environments, which has to reduce the flexibility and convenience. In addition, general deep palmprint recognition algorithms are often too heavy to meet the real-time requirements of embedded system. In this paper, a new palmprint benchmark is established, which consists of more than 20,000 images collected by 5 brands of smart phones in an unconstrained manner. Each image has been manually labeled with 14 key points for region of interest (ROI) extraction. Further, the approach called Deep Distillation Hashing (DDH) is proposed as benchmark for efficient deep palmprint recognition. Palmprint images are converted to binary codes to improve the efficiency of feature matching. Derived from knowledge distillation, novel distillation loss functions are constructed to compress deep model to further improve the efficiency of feature extraction on light network. Comprehensive experiments are conducted on both constrained and unconstrained palmprint databases. Using DDH, the accuracy of palmprint identification can be increased by up to 11.37%, and the Equal Error Rate (EER) of palmprint verification can be reduced by up to 3.11%. The results indicate the feasibility of our database, and DDH can outperform other baselines to achieve the state-of-the-art performance. The collected dataset and related source codes are publicly available at http://gr.xjtu.edu.cn/web/bell/resource.

研究动机与目标

• 为评估移动设备和可穿戴生物识别系统，解决缺乏适合真实世界无约束掌纹数据集的问题。
• 开发一种轻量级深度学习模型，实现在资源受限嵌入式设备上的实时掌纹识别。
• 通过知识蒸馏与二进制哈希技术，提升无约束条件下识别准确率并降低验证错误率。
• 建立一个公开可用的基准数据集，包含20,000张智能手机拍摄的掌纹图像，并附带14个点的感兴趣区域（ROI）标注。

提出的方法

• 使用五种不同品牌的智能手机采集了一个新的无约束掌纹数据集，包含超过20,000张图像，并对感兴趣区域（ROI）进行了人工14点标注。
• 将掌纹图像转换为紧凑的二进制编码，以加速特征匹配并降低存储与计算成本。
• 采用知识蒸馏框架，由大型教师网络指导小型学生网络，高效学习判别性特征。
• 设计了新型蒸馏损失函数，以增强从教师网络到学生网络的特征迁移，提升模型效率与准确率。
• 优化学生网络，使其生成的二进制编码在保留判别性信息的同时，最小化计算开销。

实验结果

研究问题

• RQ1 轻量级深度学习模型是否能在移动和嵌入式平台上实现无约束掌纹识别的高准确率？
• RQ2 知识蒸馏在压缩深层掌纹模型时，是否能在不损失性能的前提下有效实现？
• RQ3 二进制哈希在实时应用中，能在多大程度上提升掌纹匹配的效率？
• RQ4 在无约束数据上，所提方法与现有基线方法相比，在准确率和Equal Error Rate（EER）方面表现如何？

主要发现

• 所提出的深度蒸馏哈希（DDH）方法相比基线模型，将掌纹识别准确率最高提升了11.37%。
• 在无约束基准数据集上，DDH将掌纹验证的Equal Error Rate（EER）降低了高达3.11%。
• 新建立的基准数据集包含超过20,000张智能手机拍摄的掌纹图像及14点ROI标注，可实现对移动生物识别系统的现实评估。
• 通过DDH训练的学生网络在保持高效率的同时，实现了最先进的性能，适用于嵌入式部署。