Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN
Periocular recognition remains challenging for deployments in the unconstrained environments. Therefore, this paper proposes an RGB-OCLBCP dual-stream convolutional neural network, which accepts an RGB ocular image and a colour-based texture descriptor, namely Orthogonal Combination-Local Binary Cod...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/13/2709 |
| _version_ | 1818836407287808000 |
|---|---|
| author | Leslie Ching Ow Tiong Yunli Lee Andrew Beng Jin Teoh |
| author_facet | Leslie Ching Ow Tiong Yunli Lee Andrew Beng Jin Teoh |
| author_sort | Leslie Ching Ow Tiong |
| collection | DOAJ |
| description | Periocular recognition remains challenging for deployments in the unconstrained environments. Therefore, this paper proposes an RGB-OCLBCP dual-stream convolutional neural network, which accepts an RGB ocular image and a colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OCLBCP) for periocular recognition in the wild. The proposed network aggregates the RGB image and the OCLBCP descriptor by using two distinct late-fusion layers. We demonstrate that the proposed network benefits from the RGB image and thee OCLBCP descriptor can gain better recognition performance. A new database, namely an Ethnic-ocular database of periocular in the wild, is introduced and shared for benchmarking. In addition, three publicly accessible databases, namely AR, CASIA-iris distance and UBIPr, have been used to evaluate the proposed network. When compared against several competing networks on these databases, the proposed network achieved better performances in both recognition and verification tasks. |
| first_indexed | 2024-12-19T03:06:07Z |
| format | Article |
| id | doaj.art-5abff36f73194435a830a12b9a16906b |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-19T03:06:07Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-5abff36f73194435a830a12b9a16906b2022-12-21T20:38:06ZengMDPI AGApplied Sciences2076-34172019-07-01913270910.3390/app9132709app9132709Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNNLeslie Ching Ow Tiong0Yunli Lee1Andrew Beng Jin Teoh2Computational Science Research Center, Korea Institute of Science and Technology (KIST), Building L0243 14 gil, 5 Hwarangro, Seongbukgu, Seoul 02792, KoreaSchool of Science and Technology, Sunway University, 5 Jalan Universiti, Bandar Sunway, Petaling Jaya 47500, Selangor, MalaysiaSchool of Electrical and Electronic Engineering, Yonsei University, 50 Yonsei-ro, Sinchon-dong, Seodaemun-gu, Seoul 03722, KoreaPeriocular recognition remains challenging for deployments in the unconstrained environments. Therefore, this paper proposes an RGB-OCLBCP dual-stream convolutional neural network, which accepts an RGB ocular image and a colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OCLBCP) for periocular recognition in the wild. The proposed network aggregates the RGB image and the OCLBCP descriptor by using two distinct late-fusion layers. We demonstrate that the proposed network benefits from the RGB image and thee OCLBCP descriptor can gain better recognition performance. A new database, namely an Ethnic-ocular database of periocular in the wild, is introduced and shared for benchmarking. In addition, three publicly accessible databases, namely AR, CASIA-iris distance and UBIPr, have been used to evaluate the proposed network. When compared against several competing networks on these databases, the proposed network achieved better performances in both recognition and verification tasks.https://www.mdpi.com/2076-3417/9/13/2709periocular recognition in the wildconvolutional neural networkcolour-based local binary coded pattern |
| spellingShingle | Leslie Ching Ow Tiong Yunli Lee Andrew Beng Jin Teoh Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN Applied Sciences periocular recognition in the wild convolutional neural network colour-based local binary coded pattern |
| title | Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN |
| title_full | Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN |
| title_fullStr | Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN |
| title_full_unstemmed | Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN |
| title_short | Periocular Recognition in the Wild: Implementation of RGB-OCLBCP Dual-Stream CNN |
| title_sort | periocular recognition in the wild implementation of rgb oclbcp dual stream cnn |
| topic | periocular recognition in the wild convolutional neural network colour-based local binary coded pattern |
| url | https://www.mdpi.com/2076-3417/9/13/2709 |
| work_keys_str_mv | AT lesliechingowtiong periocularrecognitioninthewildimplementationofrgboclbcpdualstreamcnn AT yunlilee periocularrecognitioninthewildimplementationofrgboclbcpdualstreamcnn AT andrewbengjinteoh periocularrecognitioninthewildimplementationofrgboclbcpdualstreamcnn |