Investigating Deep CNNs Models Applied in Kinship Verification through Facial Images
| Autor: | Salah Eddine Bekhouche, Abdelhakim Chergui, Salim Ouchtati, Jean Sequeira, Sébastien Mavromatis |
|---|---|
| Přispěvatelé: | MODélisation Géométrique (GMOD), Laboratoire d'Informatique et Systèmes (LIS), Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS) |
| Rok vydání: | 2019 |
| Předmět: |
Computer science
SVM Kinship verication Feature extraction 0211 other engineering and technologies Feature selection 02 engineering and technology [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG] ResNet 0202 electrical engineering electronic engineering information engineering Kinship Preprocessor Rank Features 021110 strategic defence & security studies business.industry Deep learning CNNs [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Pattern recognition [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR] Support vector machine Feature (computer vision) [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] Face (geometry) Ttest 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | 5th International Conference on Frontiers of Signal Processing (ICFSP 2019) 5th International Conference on Frontiers of Signal Processing (ICFSP 2019), Sep 2019, Marseille, France HAL |
| DOI: | 10.1109/icfsp48124.2019.8938055 |
| Popis: | The kinship verification through facial images is ana ctive research topic due to its potential applications. In this paper, we propose an approach which takes two images as input then give kinship result (kinship / No-kinship) as an output. our approach based on the deep learning model (ResNet) for the feature extraction step, alongside with our proposed pair feature representation function and RankFeatures (Ttest) for feature selection to reduce the number of features finally we use the SVM classifier for the decision of kinship verification. The approach contains three steps which are: (1) face preprocessing, (2) deep features extraction and pair features representation (3) Classification. Experiments are conducted on five public databases. The experimental results show that our approach is comparable with existed approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|