A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network

Ilyass Abouelaziz,; Mohammed El Hassouni; Hocine Cherifi

A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network

Ilyass Abouelaziz, ^{1, *} Mohammed El Hassouni ^{1, *} Hocine Cherifi ^{2, *}

* Auteur correspondant

2 Le2i - Laboratoire Electronique, Informatique et Image [UMR6303]

Abstract : No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully assesses the visual quality, in addition, the experimental results show that the proposed method provides good correlations with the subject scores and competitive scores comparing to some influential and effective full and reduced reference existing metrics.

Keywords : computational geometry learning (artificial intelligence) mesh generation neural nets regression analysis INSPEC: Non-Controlled Indexing curvature based method blind mesh visual quality assessment no-reference quality assessment computational method human perceived quality prediction distorted mesh GRNN mean curvature perceptual feature visual aspect representation 3D mesh human subjective scores general regression neural network training visual quality subject scores competitive scores Author Keywords Blind mesh visual quality assessment general regression neural network mean opinion scores predicted objective scores feature learning

Type de document :

Communication dans un congrès

Domaine :

Informatique [cs] / Traitement du signal et de l'image [eess.SP]

Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01557927
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : jeudi 6 juillet 2017 - 16:26:47
Dernière modification le : vendredi 9 août 2019 - 15:10:33

A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network

Identifiants

Collections

Citation

Exporter

Métriques

66

Contact

A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network

Identifiants

Collections

Citation

Exporter

Partager

Métriques

66

Contact