Modeling and Detection of Wrinkles in Aging Human Faces Using Marked Point Processes

Nazre Batool 1 Rama Chellappa 1
1 University of Maryland Institute for Advanced Computer Studies
Abstract : In this paper we propose a new generative model for wrinkles on aging human faces using Marked Point Processes (MPP). Wrinkles are considered as stochastic spatial arrangements of sequences of line segments, and detected in an image by proper localization of line segments. The intensity gradients are used to detect more probable lo-cations and a prior probability model is used to constrain properties of line segments. Wrinkles are localized by sampling MPP using the Reversible Jump Markov Chain Monte Carlo (RJMCMC) algorithm. We also present an evaluation setup to measure the performance of the pro-posed model. We present results on a variety of images obtained from the Internet to illustrate the performance of the proposed model.
Keywords : Modeling of wrinkles Markov Point Process Reversible Jump Markov Chain Monte Carlo stochastic geometrical model
Type de document :
Communication dans un congrès
12th European Conference on Computer Vision “What’s in a Face?” Workshop, Oct 2012, Florence, Italy. pp.178 - 188, 2012, 〈10.1007/978-3-642-33868-7_18〉
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01096683
Contributeur : Nazre Batool <>
Soumis le : jeudi 18 décembre 2014 - 01:16:31
Dernière modification le : mardi 6 janvier 2015 - 01:03:44
Document(s) archivé(s) le : lundi 23 mars 2015 - 16:11:59

Fichier

Camera_Ready_2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INSMI

Citation

Nazre Batool, Rama Chellappa. Modeling and Detection of Wrinkles in Aging Human Faces Using Marked Point Processes. 12th European Conference on Computer Vision “What’s in a Face?” Workshop, Oct 2012, Florence, Italy. pp.178 - 188, 2012, 〈10.1007/978-3-642-33868-7_18〉. 〈hal-01096683〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

44

Téléchargements de fichiers

265

Contact


archive-ouverte@inria.fr