Multi-Faceted Knowledge-Driven Graph Neural Network for Iris Segmentation
文献类型：期刊论文
| 作者 | Wei, Jianze1 ; Wang, Yunlong2; Gao, Xingyu1; He, Ran2; Sun, Zhenan2
|
| 刊名 | IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
 |
| 出版日期 | 2024 |
| 卷号 | 19页码:6015-6027 |
| 关键词 | Iris Image segmentation Visualization Accuracy Correlation Annotations Semantics Iris segmentation multi-faceted knowledge graph neural network |
| ISSN号 | 1556-6013 |
| DOI | 10.1109/TIFS.2024.3407508 |
| 通讯作者 | Wang, Yunlong(yunlong.wang@cripac.ia.ac.cn) ; Gao, Xingyu(gxy9910@gmail.com) |
| 英文摘要 | Accurate iris segmentation, especially around the iris inner and outer boundaries, is still a formidable challenge. Pixels within these areas are difficult to semantically distinguish since they have similar visual characteristics and close spatial positions. To tackle this problem, the paper proposes an iris segmentation graph neural network (ISeGraph) for accurate segmentation. ISeGraph regards individual pixels as nodes within the graph and constructs self-adaptive edges according to multi-faceted knowledge, including visual similarity, positional correlation, and semantic consistency for feature aggregation. Specifically, visual similarity strengthens the connections between nodes sharing similar visual characteristics, while positional correlation assigns weights according to the spatial distance between nodes. In contrast to the above knowledge, semantic consistency maps nodes into a semantic space and learns pseudo-labels to define relationships based on label consistency. ISeGraph leverages multi-faceted knowledge to generate self-adaptive relationships for accurate iris segmentation. Furthermore, a pixel-wise adaptive normalization module is developed to increase the feature discriminability. It takes informative features in the shallow layer as a reference to improve the segmentation features from a statistical perspective. Experimental results on three iris datasets illustrate that the proposed method achieves superior performance in iris segmentation, increasing the segmentation accuracy in areas near the iris boundaries. |
| WOS关键词 | RECOGNITION |
| 资助项目 | Science and Technology Innovation (STI) 2030-Major Projects |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001248232400009 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Science and Technology Innovation (STI) 2030-Major Projects |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59020]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Wang, Yunlong; Gao, Xingyu |
| 作者单位 | 1.Chinese Acad Sci, Inst Microelect, Beijing 100029, Peoples R China 2.Chinese Acad Sci CASIA, Inst Automat, New Lab Pattern Recognit NLPR, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wei, Jianze,Wang, Yunlong,Gao, Xingyu,et al. Multi-Faceted Knowledge-Driven Graph Neural Network for Iris Segmentation[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2024,19:6015-6027. |
| APA | Wei, Jianze,Wang, Yunlong,Gao, Xingyu,He, Ran,&Sun, Zhenan.(2024).Multi-Faceted Knowledge-Driven Graph Neural Network for Iris Segmentation.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,19,6015-6027. |
| MLA | Wei, Jianze,et al."Multi-Faceted Knowledge-Driven Graph Neural Network for Iris Segmentation".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19(2024):6015-6027. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。