Syntactic texture and perception for a new generic visual anomalies classification - Archive ouverte HAL
Communication Dans Un Congrès Année : 2015

Syntactic texture and perception for a new generic visual anomalies classification

Résumé

The research purpose is to improve aesthetic anomalies detection and evaluation based on what is perceived by human eye and on the 2006 CIE report. 1 It is therefore important to dene parameters able to discriminate surfaces, in accordance with the perception of human eye. Our starting point in assessing aesthetic anomalies is geometric description such as dened by ISO standard, 2 i.e. traduce anomalies description with perception words about texture divergence impact. However, human controllers observe (detect) the aesthetic anomaly by its visual eect and interpreter for its geometric description. The research question is how dene generic parameters for discriminating aesthetic anomalies, from enhanced information of visual texture such as recent surface visual rendering approach. We propose to use an approach from visual texture processing that quantify spatial variations of pixel for translating changes in color, material and relief. From a set of images from dierent angles of light which gives us access to the surface appearance, we propose an approach from visual eect to geometrical specications as the current standards have identied the aesthetic anomalies.
Fichier principal
Vignette du fichier
Conf_Paper_20150603_SPIE_QualityControlbyArtificialVisionFR-SDesage-Fullpaper-Preprint.pdf (1.72 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02136841 , version 1 (22-05-2019)

Identifiants

Citer

Simon-Frédéric Desage, Gilles Pitard, Maurice Pillet, Hugues Favrelière, Jean-Luc Maire, et al.. Syntactic texture and perception for a new generic visual anomalies classification. Quality Control by Artificial Vision (QVAV), Jun 2015, Le Creusot, France. ⟨10.1117/12.2182819⟩. ⟨hal-02136841⟩
57 Consultations
112 Téléchargements

Altmetric

Partager

More