Cross-resolution learning for face recognition
| Autor: | Fabio Valerio Massoli, Fabrizio Falchi, Giuseppe Amato |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
I.2.6 I.2.10 Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Low resolution face recognition Machine learning computer.software_genre Convolutional neural network Facial recognition system Machine Learning (cs.LG) FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Preprocessor 10. No inequality Image resolution computer.programming_language I.2.6 I.2.10 Artificial neural network business.industry Deep learning Image and Video Processing (eess.IV) 020207 software engineering Electrical Engineering and Systems Science - Image and Video Processing Python (programming language) Cross resolution face recognition Signal Processing 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business computer |
| Zdroj: | Image and vision computing 99 (2020). doi:10.1016/j.imavis.2020.103927 info:cnr-pdr/source/autori:Massoli F.V.; Amato G.; Falchi F./titolo:Cross-resolution learning for face recognition/doi:10.1016%2Fj.imavis.2020.103927/rivista:Image and vision computing/anno:2020/pagina_da:/pagina_a:/intervallo_pagine:/volume:99 |
| DOI: | 10.1016/j.imavis.2020.103927 |
| Popis: | Convolutional Neural Network models have reached extremely high performance on the Face Recognition task. Mostly used datasets, such as VGGFace2, focus on gender, pose, and age variations, in the attempt of balancing them to empower models to better generalize to unseen data. Nevertheless, image resolution variability is not usually discussed, which may lead to a resizing of 256 pixels. While specific datasets for very low-resolution faces have been proposed, less attention has been paid on the task of cross-resolution matching. Hence, the discrimination power of a neural network might seriously degrade in such a scenario. Surveillance systems and forensic applications are particularly susceptible to this problem since, in these cases, it is common that a low-resolution query has to be matched against higher-resolution galleries. Although it is always possible to either increase the resolution of the query image or to reduce the size of the gallery (less frequently), to the best of our knowledge, extensive experimentation of cross-resolution matching was missing in the recent deep learning-based literature. In the context of low- and cross-resolution Face Recognition, the contribution of our work is fourfold: i) we proposed a training procedure to fine-tune a state-of-the-art model to empower it to extract resolution-robust deep features; ii) we conducted an extensive test campaign by using high-resolution datasets (IJB-B and IJB-C) and surveillance-camera-quality datasets (QMUL-SurvFace, TinyFace, and SCface) showing the effectiveness of our algorithm to train a resolution-robust model; iii) even though our main focus was the cross-resolution Face Recognition, by using our training algorithm we also improved upon state-of-the-art model performances considering low-resolution matches; iv) we showed that our approach could be more effective concerning preprocessing faces with super-resolution techniques. The python code of the proposed method will be available at https://github.com/fvmassoli/cross-resolution-face-recognition . |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|