Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification
Biometric recognition technology has been widely used in various fields of society. Iris recognition technology, as a stable and convenient biometric recognition technology, has been widely used in security applications. However, the iris images collected in the actual non-cooperative environment ha...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/7723 |
| _version_ | 1797470002167676928 |
|---|---|
| author | Yinyin Wei Xiangyang Zhang Aijun Zeng Huijie Huang |
| author_facet | Yinyin Wei Xiangyang Zhang Aijun Zeng Huijie Huang |
| author_sort | Yinyin Wei |
| collection | DOAJ |
| description | Biometric recognition technology has been widely used in various fields of society. Iris recognition technology, as a stable and convenient biometric recognition technology, has been widely used in security applications. However, the iris images collected in the actual non-cooperative environment have various noises. Although mainstream iris recognition methods based on deep learning have achieved good recognition accuracy, the intention is to increase the complexity of the model. On the other hand, what the actual optical system collects is the original iris image that is not normalized. The mainstream iris recognition scheme based on deep learning does not consider the iris localization stage. In order to solve the above problems, this paper proposes an effective iris recognition scheme consisting of the iris localization and iris verification stages. For the iris localization stage, we used the parallel Hough circle to extract the inner circle of the iris and the Daugman algorithm to extract the outer circle of the iris, and for the iris verification stage, we developed a new lightweight convolutional neural network. The architecture consists of a deep residual network module and a residual pooling layer which is introduced to effectively improve the accuracy of iris verification. Iris localization experiments were conducted on 400 iris images collected under a non-cooperative environment. Compared with its processing time on a graphics processing unit with a central processing unit architecture, the experimental results revealed that the speed was increased by 26, 32, 36, and 21 times at 4 different iris datasets, respectively, and the effective iris localization accuracy is achieved. Furthermore, we chose four representative iris datasets collected under a non-cooperative environment for the iris verification experiments. The experimental results demonstrated that the network structure could achieve high-precision iris verification with fewer parameters, and the equal error rates are 1.08%, 1.01%, 1.71%, and 1.11% on 4 test databases, respectively. |
| first_indexed | 2024-03-09T19:30:35Z |
| format | Article |
| id | doaj.art-42791a5219e84ef7a384ea75f3f6474b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:30:35Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-42791a5219e84ef7a384ea75f3f6474b2023-11-24T02:24:38ZengMDPI AGSensors1424-82202022-10-012220772310.3390/s22207723Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris VerificationYinyin Wei0Xiangyang Zhang1Aijun Zeng2Huijie Huang3Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai 201800, ChinaSchool of Science, Jiangnan University, Wuxi 214122, ChinaShanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai 201800, ChinaShanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai 201800, ChinaBiometric recognition technology has been widely used in various fields of society. Iris recognition technology, as a stable and convenient biometric recognition technology, has been widely used in security applications. However, the iris images collected in the actual non-cooperative environment have various noises. Although mainstream iris recognition methods based on deep learning have achieved good recognition accuracy, the intention is to increase the complexity of the model. On the other hand, what the actual optical system collects is the original iris image that is not normalized. The mainstream iris recognition scheme based on deep learning does not consider the iris localization stage. In order to solve the above problems, this paper proposes an effective iris recognition scheme consisting of the iris localization and iris verification stages. For the iris localization stage, we used the parallel Hough circle to extract the inner circle of the iris and the Daugman algorithm to extract the outer circle of the iris, and for the iris verification stage, we developed a new lightweight convolutional neural network. The architecture consists of a deep residual network module and a residual pooling layer which is introduced to effectively improve the accuracy of iris verification. Iris localization experiments were conducted on 400 iris images collected under a non-cooperative environment. Compared with its processing time on a graphics processing unit with a central processing unit architecture, the experimental results revealed that the speed was increased by 26, 32, 36, and 21 times at 4 different iris datasets, respectively, and the effective iris localization accuracy is achieved. Furthermore, we chose four representative iris datasets collected under a non-cooperative environment for the iris verification experiments. The experimental results demonstrated that the network structure could achieve high-precision iris verification with fewer parameters, and the equal error rates are 1.08%, 1.01%, 1.71%, and 1.11% on 4 test databases, respectively.https://www.mdpi.com/1424-8220/22/20/7723iris recognitioniris localizationiris verificationdeep residual networkresidual pooling layer |
| spellingShingle | Yinyin Wei Xiangyang Zhang Aijun Zeng Huijie Huang Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification Sensors iris recognition iris localization iris verification deep residual network residual pooling layer |
| title | Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification |
| title_full | Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification |
| title_fullStr | Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification |
| title_full_unstemmed | Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification |
| title_short | Iris Recognition Method Based on Parallel Iris Localization Algorithm and Deep Learning Iris Verification |
| title_sort | iris recognition method based on parallel iris localization algorithm and deep learning iris verification |
| topic | iris recognition iris localization iris verification deep residual network residual pooling layer |
| url | https://www.mdpi.com/1424-8220/22/20/7723 |
| work_keys_str_mv | AT yinyinwei irisrecognitionmethodbasedonparallelirislocalizationalgorithmanddeeplearningirisverification AT xiangyangzhang irisrecognitionmethodbasedonparallelirislocalizationalgorithmanddeeplearningirisverification AT aijunzeng irisrecognitionmethodbasedonparallelirislocalizationalgorithmanddeeplearningirisverification AT huijiehuang irisrecognitionmethodbasedonparallelirislocalizationalgorithmanddeeplearningirisverification |