Face Sketch Synthesis using Generative Adversarial Networks

Sami, Mahfoud; Abdelhamid, Daamouche; Messaoud, Bengherabi; Elhocine, Boutellaa; Hadid, Abdenour

Type de document :

Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes

Titre :

Face Sketch Synthesis using Generative Adversarial Networks

Auteur(s) :

Sami, Mahfoud [Auteur]
Abdelhamid, Daamouche [Auteur]
Messaoud, Bengherabi [Auteur]
Elhocine, Boutellaa [Auteur]
Hadid, Abdenour [Auteur]
Sorbonne University Abu Dhabi [SUAD]
COMmunications NUMériques - IEMN [COMNUM - IEMN]

Titre de la manifestation scientifique :

TAMARICS

Ville :

Tamanrasset

Pays :

Algérie

Date de début de la manifestation scientifique :

2022

Mot(s)-clé(s) en anglais :

Face Sketch Synthesis
Face Sketch Recognition
Image Quality Assessment
Generative Adversarial Networks

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]

Résumé en anglais : [en]

Face Sketch Synthesis is crucial for a wide range of practical applications, including digital entertainment and law enforcement. Recent approaches based on GenerativeAdversarial Networks (GANs) have shown compelling results ...
Lire la suite >Face Sketch Synthesis is crucial for a wide range of practical applications, including digital entertainment and law enforcement. Recent approaches based on GenerativeAdversarial Networks (GANs) have shown compelling results in image-to-image translation as well as face photo-sketch synthesis. However, these methods still have considerable limitations as some noise appears in synthesized sketches which leads to poor perceptual quality and poor preserving fidelity. To tackle this issue, in this paper, we propose aFace Sketch Synthesis technique using conditional GAN to generate facial sketches from facial photographs named cGAN-FSS. Our cGAN-FSS framework generates high perceptualquality of face sketch synthesis while maintaining high identity recognition accuracy. Image Quality Assessment metrics and Face Recognition experiments confirm our proposedframework’s performs better than the state-of-the-art methods.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL

Face Sketch Synthesis using Generative ... BibTeX CSV Excel RIS

Face Sketch Synthesis using Generative ...

BibTeX

CSV

Excel

RIS