A Hybrid Model Combining Learning Distance Metric and DAG Support Vector Machine for Multimodal Biometric Recognition
A Hybrid Model Combining Learning Distance Metric and DAG Support Vector Machine for Multimodal Biometric Recognition
复制标题
一种结合学习距离度量和 DAG 支持向量机的多模态生物特征识别混合模型
DOI：
10.1109/access.2020.3035110
复制
发表时间：
2021
期刊：
影响因子：
3.9
通讯作者：
Song Enmin
中科院分区：
文献类型：
--
作者：
Omara Ibrahim;Hagag Ahmed;Chaib Souleyman;Ma Guangzhi;Abd El-Samie Fathi E.;Song Enmin
度量学习显著改善了机器学习应用，如人脸再识别和使用k -最近邻（KNN）和支持向量机（SVM）分类器的图像分类。然而，据我们所知，它还没有被调查过，特别是在移民、法医和监控应用中使用不受控制的耳朵数据集的多模态生物识别问题。因此，提出一种基于核支持向量机的基于学习距离度量（LDM）的多模态生物特征识别新框架是非常有趣和有吸引力的。本文通过研究一种用于多模态生物特征识别的混合学习距离度量和有向无环图支持向量机（LDM-DAGSVM）模型来考虑SVM的度量学习，其中LDM和DAGSVM是处理分类问题的两种新兴技术。与现有的多模态生物特征识别方法不同，该方法旨在通过核支持向量机学习马氏距离度量，同时最大化类间变化和最小化类内变化。在非受控数据集（如AR人脸和AWE耳朵数据集）上的实验结果表明，与处理单个模态的模型相比，所提出的方法取得了具有竞争力的性能，并且优于最先进的多模态方法。该模型对人脸和耳朵图像的分类准确率达到99.85%左右，达到5倍。
Metric learning has significantly improved machine learning applications such as face re-identification and image classification using K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) classifiers. However, to the best of our knowledge, it has not been investigated yet, especially for the multimodal biometric recognition problem in immigration, forensic and surveillance applications with uncontrolled ear datasets. Therefore, it is interesting and very attractive to propose a novel framework for multimodal biometric recognition based on Learning Distance Metric (LDM) via kernel SVM. This paper considers metric learning for SVM by investigating a hybrid Learning Distance Metric and Directed Acyclic Graph SVM (LDM-DAGSVM) model for multimodal biometric recognition, where LDM and DAGSVM are two emerging techniques in dealing with classification problems. Different from existing multimodal biometric recognition methods, the proposed approach aims to learn Mahalanobis distance metric via kernel SVM to maximize the inter-class variations and minimize the intra-class variations, simultaneously. Experimental results on the uncontrolled datasets such as AR face and AWE ear datasets show that the proposed approach achieves competitive performance compared with models working on individual modalities and overperforms the state-of-the-art multimodal methods. The proposed model achieves five-fold classification accuracy around 99.85 % for the face and ear images.
登录
查看更多内容
具有动态生成的成对约束的度量学习用于耳朵识别
影响因子：
3.1
作者：
Ibrahim Omara;Hongzhi Zhang;Faqiang Wang;Ahmed Hagag;Xiaoming Li;Wangmeng Zuo
通讯作者：
Wangmeng Zuo
DOI：
10.1109/tpami.2007.1005
发表时间：
2007-04-01
影响因子：
23.6
作者：
Chen, Hui;Bhanu, Bir
通讯作者：
Bhanu, Bir
DOI：
10.1016/j.patrec.2015.05.001
发表时间：
2015-12
期刊：
Pattern Recognit. Lett.
影响因子：
--
作者：
Venice Erin Liong;Jiwen Lu;Yongxin Ge
通讯作者：
Venice Erin Liong;Jiwen Lu;Yongxin Ge
影响因子：
5.6
作者：
Saiyed Umer;B. Dhara;B. Chanda
通讯作者：
Saiyed Umer;B. Dhara;B. Chanda
DOI：
10.1145/3230820.3230832
发表时间：
2018-05
期刊：
--
影响因子：
--
作者：
Ibrahim Omara;Ahmed M. Hagag;W. Zuo
通讯作者：
Ibrahim Omara;Ahmed M. Hagag;W. Zuo