dc.contributor.author | Khodabakhsh, Ali | |
dc.contributor.author | Pedersen, Marius | |
dc.contributor.author | Busch, Christoph | |
dc.date.accessioned | 2019-11-07T12:41:52Z | |
dc.date.available | 2019-11-07T12:41:52Z | |
dc.date.created | 2019-06-24T18:44:46Z | |
dc.date.issued | 2019 | |
dc.identifier.isbn | 978-1-4503-6305-1 | |
dc.identifier.uri | http://hdl.handle.net/11250/2627212 | |
dc.description.abstract | The performance of any face recognition system gets affected by the quality of the probe and the reference images. Rejecting or recapturing images with low-quality can improve the overall performance of the biometric system. There are many statistical as well as learning-based methods that provide quality scores given an image for the task of face recognition.
In this study, we take a different approach by asking 26 participants to provide subjective quality scores that represent the ease of recognizing the face on the images from a smartphone based face image dataset. These scores are then compared to measures implemented from ISO/IEC TR 29794-5. We observe that the subjective scores outperform the implemented objective scores while having a low correlation with them. Furthermore, we analyze the effect of pose, illumination, and distance on face recognition similarity scores as well as the generated mean opinion scores. | nb_NO |
dc.language.iso | eng | nb_NO |
dc.publisher | Association for Computing Machinery (ACM) | nb_NO |
dc.relation.ispartof | Proceedings of the 2019 International Conference on Biometrics Engineering and Application (ICBEA 2019) | |
dc.title | Subjective Versus Objective Face Image Quality Evaluation For Face Recognition | nb_NO |
dc.type | Chapter | nb_NO |
dc.description.version | publishedVersion | nb_NO |
dc.identifier.doi | 10.1145/3345336.3345338 | |
dc.identifier.cristin | 1707381 | |
dc.description.localcode | This article will not be available due to copyright restrictions (c) 2019 by Association for Computing Machinery (ACM) | nb_NO |
cristin.unitcode | 194,63,30,0 | |
cristin.unitcode | 194,63,10,0 | |
cristin.unitname | Institutt for informasjonssikkerhet og kommunikasjonsteknologi | |
cristin.unitname | Institutt for datateknologi og informatikk | |
cristin.ispublished | false | |
cristin.fulltext | preprint | |
cristin.qualitycode | 1 | |