QDF: A face database with varying quality
| Autor: | Shubhobrata Bhattacharya, Aurobinda Routray, Suparna Rooj |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Database
Biometrics Quality assessment Computer science media_common.quotation_subject ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020206 networking & telecommunications Image processing 02 engineering and technology computer.software_genre Facial recognition system Face (geometry) Signal Processing 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Quality (business) Computer Vision and Pattern Recognition Point estimation Electrical and Electronic Engineering Unavailability computer Software media_common |
| Zdroj: | Signal Processing: Image Communication. 74:13-20 |
| ISSN: | 0923-5965 |
| DOI: | 10.1016/j.image.2018.12.013 |
| Popis: | Face Recognition is one of the well-researched areas of biometrics. Although many researchers have shown considerable interest, the problems still persist because of unpredictable environmental factors affecting the acquisition of real-life face images. One of the major factors that causes poor recognition performance of the most face recognition algorithms is due to the unavailability of a proper training dataset which reflects real-life scenarios. In this paper, we propose a face dataset, of about 100 subjects, with varying degree of quality in terms of distance from the camera, ambient illumination, pose variations and natural occlusions. This database can be used to train systems with real-life face images. The face quality of this dataset has been quantified with popular Face Quality Assessment (FQA) algorithms. We have also tested this database with standard face recognition, super-resolution image processing and fiducial point estimation algorithms. Database is available to research community through https://sites.google.com/view/quality-based-distance-face-da/ . |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect