An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network
Recently, deep learning approaches, especially convolutional neural networks (CNNs), have attracted extensive attention in iris recognition. Though CNN-based approaches realize automatic feature extraction and achieve outstanding performance, they usually require more training samples and higher com...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/11/3721 |
| _version_ | 1797532484561272832 |
|---|---|
| author | Guoyang Liu Weidong Zhou Lan Tian Wei Liu Yingjian Liu Hanwen Xu |
| author_facet | Guoyang Liu Weidong Zhou Lan Tian Wei Liu Yingjian Liu Hanwen Xu |
| author_sort | Guoyang Liu |
| collection | DOAJ |
| description | Recently, deep learning approaches, especially convolutional neural networks (CNNs), have attracted extensive attention in iris recognition. Though CNN-based approaches realize automatic feature extraction and achieve outstanding performance, they usually require more training samples and higher computational complexity than the classic methods. This work focuses on training a novel condensed 2-channel (2-ch) CNN with few training samples for efficient and accurate iris identification and verification. A multi-branch CNN with three well-designed online augmentation schemes and radial attention layers is first proposed as a high-performance basic iris classifier. Then, both branch pruning and channel pruning are achieved by analyzing the weight distribution of the model. Finally, fast finetuning is optionally applied, which can significantly improve the performance of the pruned CNN while alleviating the computational burden. In addition, we further investigate the encoding ability of 2-ch CNN and propose an efficient iris recognition scheme suitable for large database application scenarios. Moreover, the gradient-based analysis results indicate that the proposed algorithm is robust to various image contaminations. We comprehensively evaluated our algorithm on three publicly available iris databases for which the results proved satisfactory for real-time iris recognition. |
| first_indexed | 2024-03-10T10:59:50Z |
| format | Article |
| id | doaj.art-d1c05862f6ea447b9b2315f3d989d18d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:59:50Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d1c05862f6ea447b9b2315f3d989d18d2023-11-21T21:35:03ZengMDPI AGSensors1424-82202021-05-012111372110.3390/s21113721An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural NetworkGuoyang Liu0Weidong Zhou1Lan Tian2Wei Liu3Yingjian Liu4Hanwen Xu5School of Microelectronics, Shandong University, Jinan 250100, ChinaSchool of Microelectronics, Shandong University, Jinan 250100, ChinaSchool of Microelectronics, Shandong University, Jinan 250100, ChinaSchool of Microelectronics, Shandong University, Jinan 250100, ChinaSchool of Microelectronics, Shandong University, Jinan 250100, ChinaSchool of Microelectronics, Shandong University, Jinan 250100, ChinaRecently, deep learning approaches, especially convolutional neural networks (CNNs), have attracted extensive attention in iris recognition. Though CNN-based approaches realize automatic feature extraction and achieve outstanding performance, they usually require more training samples and higher computational complexity than the classic methods. This work focuses on training a novel condensed 2-channel (2-ch) CNN with few training samples for efficient and accurate iris identification and verification. A multi-branch CNN with three well-designed online augmentation schemes and radial attention layers is first proposed as a high-performance basic iris classifier. Then, both branch pruning and channel pruning are achieved by analyzing the weight distribution of the model. Finally, fast finetuning is optionally applied, which can significantly improve the performance of the pruned CNN while alleviating the computational burden. In addition, we further investigate the encoding ability of 2-ch CNN and propose an efficient iris recognition scheme suitable for large database application scenarios. Moreover, the gradient-based analysis results indicate that the proposed algorithm is robust to various image contaminations. We comprehensively evaluated our algorithm on three publicly available iris databases for which the results proved satisfactory for real-time iris recognition.https://www.mdpi.com/1424-8220/21/11/3721iris recognitiononline augmentationconvolutional neural networkdeep learningnetwork pruning |
| spellingShingle | Guoyang Liu Weidong Zhou Lan Tian Wei Liu Yingjian Liu Hanwen Xu An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network Sensors iris recognition online augmentation convolutional neural network deep learning network pruning |
| title | An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network |
| title_full | An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network |
| title_fullStr | An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network |
| title_full_unstemmed | An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network |
| title_short | An Efficient and Accurate Iris Recognition Algorithm Based on a Novel Condensed 2-ch Deep Convolutional Neural Network |
| title_sort | efficient and accurate iris recognition algorithm based on a novel condensed 2 ch deep convolutional neural network |
| topic | iris recognition online augmentation convolutional neural network deep learning network pruning |
| url | https://www.mdpi.com/1424-8220/21/11/3721 |
| work_keys_str_mv | AT guoyangliu anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT weidongzhou anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT lantian anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT weiliu anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT yingjianliu anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT hanwenxu anefficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT guoyangliu efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT weidongzhou efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT lantian efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT weiliu efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT yingjianliu efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork AT hanwenxu efficientandaccurateirisrecognitionalgorithmbasedonanovelcondensed2chdeepconvolutionalneuralnetwork |