A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks
A 3D model of the human iris provides an additional degree of freedom in iris recognition, which could help identify people in larger databases, even when only a piece of the iris is available. Previously, we reported developing a 3D iris scanner that uses 2D images of the iris from multiple perspec...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9097841/ |
| _version_ | 1818736508514861056 |
|---|---|
| author | Daniel P. Benalcazar Jorge E. Zambrano Diego Bastias Claudio A. Perez Kevin W. Bowyer |
| author_facet | Daniel P. Benalcazar Jorge E. Zambrano Diego Bastias Claudio A. Perez Kevin W. Bowyer |
| author_sort | Daniel P. Benalcazar |
| collection | DOAJ |
| description | A 3D model of the human iris provides an additional degree of freedom in iris recognition, which could help identify people in larger databases, even when only a piece of the iris is available. Previously, we reported developing a 3D iris scanner that uses 2D images of the iris from multiple perspectives to reconstruct a 3D model of the iris. This paper focuses on the development of a 3D iris scanner from a single image by means of a Convolutional Neural Network (CNN). The method is based on a depth-estimation CNN for the 3D iris model. A dataset of 26,520 real iris images from 120 subjects, and a dataset of 72,000 synthetic iris images with their aligned depthmaps were created. With these datasets, we trained and compared the depth estimation capabilities of available CNN architectures. We analyzed the performance of our method to estimate the iris depth in multiple ways: using real step pyramid printed 3D models, comparing the results to those of a test set of synthetic images, comparing the results to those of the OCT scans from both eyes of one subject, and generating the 3D rubber sheet from the 3D iris model proving the correspondence with the resulting 2D rubber sheet and binary codes. On a preliminary test the proposed 3D rubber sheet model increased iris recognition performance by 48% with respect to the standard 2D iris code. Other contributions include assessing the scanning resolution, reducing the acquisition and processing time to produce the 3D iris model, and reducing the complexity of the image acquisition system. |
| first_indexed | 2024-12-18T00:38:16Z |
| format | Article |
| id | doaj.art-32df38fc8aa34fd2b7a1638b675e97a9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:38:16Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-32df38fc8aa34fd2b7a1638b675e97a92022-12-21T21:26:57ZengIEEEIEEE Access2169-35362020-01-018985849859910.1109/ACCESS.2020.29965639097841A 3D Iris Scanner From a Single Image Using Convolutional Neural NetworksDaniel P. Benalcazar0https://orcid.org/0000-0002-2030-9449Jorge E. Zambrano1https://orcid.org/0000-0002-1539-7093Diego Bastias2https://orcid.org/0000-0002-5169-5901Claudio A. Perez3https://orcid.org/0000-0002-5484-4159Kevin W. Bowyer4https://orcid.org/0000-0002-7562-4390Department of Electrical Engineering, Universidad de Chile, Santiago, ChileDepartment of Electrical Engineering, Universidad de Chile, Santiago, ChileDepartment of Electrical Engineering, Universidad de Chile, Santiago, ChileDepartment of Electrical Engineering, Universidad de Chile, Santiago, ChileDepartment of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USAA 3D model of the human iris provides an additional degree of freedom in iris recognition, which could help identify people in larger databases, even when only a piece of the iris is available. Previously, we reported developing a 3D iris scanner that uses 2D images of the iris from multiple perspectives to reconstruct a 3D model of the iris. This paper focuses on the development of a 3D iris scanner from a single image by means of a Convolutional Neural Network (CNN). The method is based on a depth-estimation CNN for the 3D iris model. A dataset of 26,520 real iris images from 120 subjects, and a dataset of 72,000 synthetic iris images with their aligned depthmaps were created. With these datasets, we trained and compared the depth estimation capabilities of available CNN architectures. We analyzed the performance of our method to estimate the iris depth in multiple ways: using real step pyramid printed 3D models, comparing the results to those of a test set of synthetic images, comparing the results to those of the OCT scans from both eyes of one subject, and generating the 3D rubber sheet from the 3D iris model proving the correspondence with the resulting 2D rubber sheet and binary codes. On a preliminary test the proposed 3D rubber sheet model increased iris recognition performance by 48% with respect to the standard 2D iris code. Other contributions include assessing the scanning resolution, reducing the acquisition and processing time to produce the 3D iris model, and reducing the complexity of the image acquisition system.https://ieeexplore.ieee.org/document/9097841/3D iris reconstruction3D iris scannerbiometricsiris recognitiondepth estimation |
| spellingShingle | Daniel P. Benalcazar Jorge E. Zambrano Diego Bastias Claudio A. Perez Kevin W. Bowyer A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks IEEE Access 3D iris reconstruction 3D iris scanner biometrics iris recognition depth estimation |
| title | A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks |
| title_full | A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks |
| title_fullStr | A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks |
| title_full_unstemmed | A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks |
| title_short | A 3D Iris Scanner From a Single Image Using Convolutional Neural Networks |
| title_sort | 3d iris scanner from a single image using convolutional neural networks |
| topic | 3D iris reconstruction 3D iris scanner biometrics iris recognition depth estimation |
| url | https://ieeexplore.ieee.org/document/9097841/ |
| work_keys_str_mv | AT danielpbenalcazar a3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT jorgeezambrano a3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT diegobastias a3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT claudioaperez a3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT kevinwbowyer a3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT danielpbenalcazar 3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT jorgeezambrano 3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT diegobastias 3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT claudioaperez 3dirisscannerfromasingleimageusingconvolutionalneuralnetworks AT kevinwbowyer 3dirisscannerfromasingleimageusingconvolutionalneuralnetworks |