Biological features De-identification in iris images

Heng Zhang, Huan Zhou, Wenming Jiao, Jie Shi, Qiyan Zang, Jing Sun, Jian Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Biometric authentication has recently become hugely popular in mobile social networks. Iris recognition, a typical biometric authentication technology, has been widely used in many fields. However, it can lead to serious consequences if the iris feature information is utilized by an illegal party. Thus, a critical issue is how to preserve iris features when the human's images are used in mobile social networks. In this paper, we first introduce an approach to identify the iris area in an eye image. By means of differential privacy, we present a de-identification algorithm on the iris area to preserve iris biological features. A remarkable advantage of our approach is that it only conceals the iris biological features but does not change the other parts of the given image. A simulation example is provided to show the effectiveness of our de-identification method at last.

Original languageEnglish
Title of host publicationProceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages67-71
Number of pages5
ISBN (Electronic)9781538685341
DOIs
StatePublished - 2 Jul 2018
Externally publishedYes
Event15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018 - Yichang, China
Duration: 16 Oct 201818 Oct 2018

Publication series

NameProceedings - 2018 15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018

Conference

Conference15th International Symposium on Pervasive Systems, Algorithms and Networks, I-SPAN 2018
Country/TerritoryChina
CityYichang
Period16/10/1818/10/18

Fingerprint

Dive into the research topics of 'Biological features De-identification in iris images'. Together they form a unique fingerprint.

Cite this