Biological Features De-identification in Iris Images
| Autor: | Huan Zhou, Jing Sun, Heng Zhang, Jie Shi, Jian Zhang, Qiyan Zang, Jiao Wenming |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Authentication
Biometrics Computer science business.industry 020208 electrical & electronic engineering Iris recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION De-identification 020206 networking & telecommunications 02 engineering and technology ComputingMilieux_MANAGEMENTOFCOMPUTINGANDINFORMATIONSYSTEMS ComputingMethodologies_PATTERNRECOGNITION medicine.anatomical_structure Feature (computer vision) 0202 electrical engineering electronic engineering information engineering medicine Differential privacy Computer vision Artificial intelligence Iris (anatomy) business |
| Zdroj: | I-SPAN |
| DOI: | 10.1109/i-span.2018.00020 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|