Boosting multi-modal ocular recognition via spatial feature reconstruction and unsupervised image quality estimation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Boosting multi-modal ocular recognition via spatial feature reconstruction and unsupervised image quality estimation
	Yan ZH(闫紫徽)1,2; He LX(何凌霄)1,2; Wang YL(王云龙)1,2; Zhang KB(张堃博)1,2; Sun ZN(孙哲南)1,2
刊名	Machine Intelligence Research
	2023-01
页码	已接收
英文摘要	In the daily application of an iris-recognition-at-a-distance (IAAD) sys tem, many ocular images of low quality are acquired. As the iris part of these images is often not qualified for the recognition requirements, the more accessible periocular regions are a good complement for recognition. To further boost the performance of IAAD systems, a novel end-to-end framework for multi-modal ocular recognition is proposed. The pro posed framework mainly consists of iris/periocualr feature extraction and matching, unsupervised iris quality assessment, and a score-level adaptive weighted fusion strategy. First, ocular feature reconstruction (OFR) is proposed to sparsely reconstruct each probe image by high quality gallery images based on proper feature maps. Next, a brand new unsupervised iris quality assessment method based on random mul tiscale embedding robustness is proposed. Different from the existing iris quality assessment methods, the quality of an iris image is mea sured by its robustness in the embedding space. At last, the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular regions. Extensive experimental results on ocular datasets prove that the pro posed method is obviously better than unimodal biometrics, and the fusion strategy can significantly improve the recognition performance.
语种	英语
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/51859]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Wang YL(王云龙)
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. Boosting multi-modal ocular recognition via spatial feature reconstruction and unsupervised image quality estimation[J]. Machine Intelligence Research,2023:已接收.
APA	Yan ZH,He LX,Wang YL,Zhang KB,&Sun ZN.(2023).Boosting multi-modal ocular recognition via spatial feature reconstruction and unsupervised image quality estimation.Machine Intelligence Research,已接收.
MLA	Yan ZH,et al."Boosting multi-modal ocular recognition via spatial feature reconstruction and unsupervised image quality estimation".Machine Intelligence Research (2023):已接收.