Hand-drawn face sketch recognition using ...
Document type :
Compte-rendu et recension critique d'ouvrage
Title :
Hand-drawn face sketch recognition using rank-level fusion of image quality assessment metrics
Author(s) :
Sami, Mahfoud [Auteur]
Université M'Hamed Bougara Boumerdes [UMBB]
Abdelhamid, Daamouche [Auteur]
Université M'Hamed Bougara Boumerdes [UMBB]
Messaoud, Bengherabi [Auteur]
Centre de Développement des Technologies Avancées [CDTA]
Hadid, Abdenour [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Sorbonne University Abu Dhabi [SUAD]
Université M'Hamed Bougara Boumerdes [UMBB]
Abdelhamid, Daamouche [Auteur]
Université M'Hamed Bougara Boumerdes [UMBB]
Messaoud, Bengherabi [Auteur]
Centre de Développement des Technologies Avancées [CDTA]
Hadid, Abdenour [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Sorbonne University Abu Dhabi [SUAD]
Journal title :
Bulletin of the Polish Academy of Sciences: Technical Sciences
Pages :
e143554
Publisher :
Polish Academy of Sciences
Publication date :
2022
ISSN :
2300-1917
English keyword(s) :
face sketch recognition
synthesized face sketch
rank-level fusion
IQA metrics
synthesized face sketch
rank-level fusion
IQA metrics
HAL domain(s) :
Informatique [cs]/Intelligence artificielle [cs.AI]
English abstract : [en]
Face Sketch Recognition (FSR) presents a severe challenge to conventional recognition paradigms developed basically to matchface photos. This challenge is mainly due to the large texture discrepancy between face sketches, ...
Show more >Face Sketch Recognition (FSR) presents a severe challenge to conventional recognition paradigms developed basically to matchface photos. This challenge is mainly due to the large texture discrepancy between face sketches, characterized by shape exaggeration, and facephotos. In this paper, we propose a training-free synthesized face sketch recognition method based on the rank-level fusion of multiple ImageQuality Assessment (IQA) metrics. The advantages of IQA metrics as a recognition engine are combined with the rank-level fusion to boost thefinal recognition accuracy. By integrating multiple IQA metrics into the face sketch recognition framework, the proposed method simultaneouslyperforms face-sketch matching application and evaluates the performance of face sketch synthesis methods. To test the performance of the recognition framework, five synthesized face sketch methods are used to generate sketches from face photos. We use the Borda count approach to fusefour IQA metrics, namely, structured similarity index metric, feature similarity index metric, visual information fidelity and gradient magnitudesimilarity deviation at the rank-level. Experimental results and comparison with the state-of-the-art methods illustrate the competitiveness of theproposed synthesized face sketch recognition framework.Show less >
Show more >Face Sketch Recognition (FSR) presents a severe challenge to conventional recognition paradigms developed basically to matchface photos. This challenge is mainly due to the large texture discrepancy between face sketches, characterized by shape exaggeration, and facephotos. In this paper, we propose a training-free synthesized face sketch recognition method based on the rank-level fusion of multiple ImageQuality Assessment (IQA) metrics. The advantages of IQA metrics as a recognition engine are combined with the rank-level fusion to boost thefinal recognition accuracy. By integrating multiple IQA metrics into the face sketch recognition framework, the proposed method simultaneouslyperforms face-sketch matching application and evaluates the performance of face sketch synthesis methods. To test the performance of the recognition framework, five synthesized face sketch methods are used to generate sketches from face photos. We use the Borda count approach to fusefour IQA metrics, namely, structured similarity index metric, feature similarity index metric, visual information fidelity and gradient magnitudesimilarity deviation at the rank-level. Experimental results and comparison with the state-of-the-art methods illustrate the competitiveness of theproposed synthesized face sketch recognition framework.Show less >
Language :
Anglais
Popular science :
Non
Source :
Files
- BPASTS_2022_70_6_3056.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- hand.drawn.faces.sketch-BPASTS_2022_MAHFOUD.pdf
- Open access
- Access the document