Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images
Abstract We address the use of selfie ocular images captured with smartphones to estimate age and gender. Partial face occlusion has become an issue due to the mandatory use of face masks. Also, the use of mobile devices has exploded, with the pandemic further accelerating the migration to digital s...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-09-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559556017782784 |
|---|---|
| author | Fernando Alonso‐Fernandez Kevin Hernandez‐Diaz Silvia Ramis Francisco J. Perales Josef Bigun |
| author_facet | Fernando Alonso‐Fernandez Kevin Hernandez‐Diaz Silvia Ramis Francisco J. Perales Josef Bigun |
| author_sort | Fernando Alonso‐Fernandez |
| collection | DOAJ |
| description | Abstract We address the use of selfie ocular images captured with smartphones to estimate age and gender. Partial face occlusion has become an issue due to the mandatory use of face masks. Also, the use of mobile devices has exploded, with the pandemic further accelerating the migration to digital services. However, state‐of‐the‐art solutions in related tasks such as identity or expression recognition employ large Convolutional Neural Networks, whose use in mobile devices is infeasible due to hardware limitations and size restrictions of downloadable applications. To counteract this, we adapt two existing lightweight CNNs proposed in the context of the ImageNet Challenge, and two additional architectures proposed for mobile face recognition. Since datasets for soft‐biometrics prediction using selfie images are limited, we counteract over‐fitting by using networks pre‐trained on ImageNet. Furthermore, some networks are further pre‐trained for face recognition, for which very large training databases are available. Since both tasks employ similar input data, we hypothesise that such strategy can be beneficial for soft‐biometrics estimation. A comprehensive study of the effects of different pre‐training over the employed architectures is carried out, showing that, in most cases, a better accuracy is obtained after the networks have been fine‐tuned for face recognition. |
| format | Article |
| id | doaj-art-5a67f406c63548fcb76c49a9ced900d6 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2021-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-5a67f406c63548fcb76c49a9ced900d62025-02-03T01:29:42ZengWileyIET Biometrics2047-49382047-49462021-09-0110556258010.1049/bme2.12046Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular imagesFernando Alonso‐Fernandez0Kevin Hernandez‐Diaz1Silvia Ramis2Francisco J. Perales3Josef Bigun4School of Information Technology Halmstad University SwedenSchool of Information Technology Halmstad University SwedenComputer Graphics and Vision and AI Group University of Balearic Islands SpainComputer Graphics and Vision and AI Group University of Balearic Islands SpainSchool of Information Technology Halmstad University SwedenAbstract We address the use of selfie ocular images captured with smartphones to estimate age and gender. Partial face occlusion has become an issue due to the mandatory use of face masks. Also, the use of mobile devices has exploded, with the pandemic further accelerating the migration to digital services. However, state‐of‐the‐art solutions in related tasks such as identity or expression recognition employ large Convolutional Neural Networks, whose use in mobile devices is infeasible due to hardware limitations and size restrictions of downloadable applications. To counteract this, we adapt two existing lightweight CNNs proposed in the context of the ImageNet Challenge, and two additional architectures proposed for mobile face recognition. Since datasets for soft‐biometrics prediction using selfie images are limited, we counteract over‐fitting by using networks pre‐trained on ImageNet. Furthermore, some networks are further pre‐trained for face recognition, for which very large training databases are available. Since both tasks employ similar input data, we hypothesise that such strategy can be beneficial for soft‐biometrics estimation. A comprehensive study of the effects of different pre‐training over the employed architectures is carried out, showing that, in most cases, a better accuracy is obtained after the networks have been fine‐tuned for face recognition.https://doi.org/10.1049/bme2.12046biometrics (access control)face recognitionimage classificationimage sensorslearning (artificial intelligence)mobile computing |
| spellingShingle | Fernando Alonso‐Fernandez Kevin Hernandez‐Diaz Silvia Ramis Francisco J. Perales Josef Bigun Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images IET Biometrics biometrics (access control) face recognition image classification image sensors learning (artificial intelligence) mobile computing |
| title | Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images |
| title_full | Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images |
| title_fullStr | Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images |
| title_full_unstemmed | Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images |
| title_short | Facial masks and soft‐biometrics: Leveraging face recognition CNNs for age and gender prediction on mobile ocular images |
| title_sort | facial masks and soft biometrics leveraging face recognition cnns for age and gender prediction on mobile ocular images |
| topic | biometrics (access control) face recognition image classification image sensors learning (artificial intelligence) mobile computing |
| url | https://doi.org/10.1049/bme2.12046 |
| work_keys_str_mv | AT fernandoalonsofernandez facialmasksandsoftbiometricsleveragingfacerecognitioncnnsforageandgenderpredictiononmobileocularimages AT kevinhernandezdiaz facialmasksandsoftbiometricsleveragingfacerecognitioncnnsforageandgenderpredictiononmobileocularimages AT silviaramis facialmasksandsoftbiometricsleveragingfacerecognitioncnnsforageandgenderpredictiononmobileocularimages AT franciscojperales facialmasksandsoftbiometricsleveragingfacerecognitioncnnsforageandgenderpredictiononmobileocularimages AT josefbigun facialmasksandsoftbiometricsleveragingfacerecognitioncnnsforageandgenderpredictiononmobileocularimages |