Flexible Iris Matching Based on Spatial Feature Reconstruction | |
Yan ZH(闫紫徽)1,2; He LX(何凌霄)1,2; Wang YL(王云龙)1,2; Sun ZN(孙哲南)1,2; Tan TN(谭铁牛)1,2 | |
刊名 | IEEE Transactions on Biometrics, Behavior, and Identity Science |
2021-08 | |
页码 | Early Access |
关键词 | Iris recognition,Image reconstruction, Feature extraction,Strain, Biometrics (access control) , Image recognition, Pupils |
ISSN号 | 2637-6407 |
DOI | 10.1109/TBIOM.2021.3108559 |
英文摘要 | In an iris recognition-at-a-distance (IAAD) system used in surveillance scenarios, the camera usually captures a large number of low-quality images. These images exhibit partial occlusions due to eyelids and eyelashes, specular reflections, and severe deformations caused by pupil dilations and contractions. Recognizing these low-quality images is a challenging yet dominant problem in IAAD. To mitigate this issue, current iris recognition systems mostly filter out low-quality images by using strict criteria based on image quality evaluation. This strategy, however, wastes device capabilities and produces low throughput of subjects. Other systems require highly cooperative users. In this work, we propose a novel occlusion-robust, deformation-robust, and alignment-free framework for low-quality iris matching, which integrates the merits of deep features and sparse representation in an end-to-end learning process known as iris spatial feature reconstruction (ISFR). Here each probe image can be sparsely reconstructed on the basis of appropriate feature maps from gallery high-quality images. ISFR uses the error from robust reconstruction over spatial pyramid features to measure similarities between two iris images, which naturally avoids the time-consuming alignment step. In summary, the distinctiveness of deep features, the robustness of sparse reconstruction, and the flexibility of multiscale matching strategy are unified in a general framework to attain more accurate and reasonable iris matching. Extensive experimental results on four public iris image databases demonstrate that the proposed method significantly outperforms both traditional and deep learning-based iris recognition methods. |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/51881] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Tan TN(谭铁牛) |
作者单位 | 1.中国科学院大学 2.中科院自动化所 |
推荐引用方式 GB/T 7714 | Yan ZH,He LX,Wang YL,et al. Flexible Iris Matching Based on Spatial Feature Reconstruction[J]. IEEE Transactions on Biometrics, Behavior, and Identity Science,2021:Early Access. |
APA | Yan ZH,He LX,Wang YL,Sun ZN,&Tan TN.(2021).Flexible Iris Matching Based on Spatial Feature Reconstruction.IEEE Transactions on Biometrics, Behavior, and Identity Science,Early Access. |
MLA | Yan ZH,et al."Flexible Iris Matching Based on Spatial Feature Reconstruction".IEEE Transactions on Biometrics, Behavior, and Identity Science (2021):Early Access. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论