Open AccessFlyBy CNN: a 3D surface segmentation framework
Author(s) -
Louis Boubolo,
Maxime Dumont,
Serge Brosset,
Jonas Bianchi,
Antônio Carlos de Oliveira Ruellas,
Marcela Gurgel,
Camila Massaro,
Arón Aliaga-Del Castillo,
Marcos Ioshida,
Marília Yatabe,
Erika Benavides,
Héctor F. Ríos,
Fabia. Soki,
Gisele Neiva,
Beatriz Paniagua,
Lucia Cevidanes,
Martin Styner,
Juan Carlos Prieto
Publication year - 2021
Publication title -
pubmed central
Language(s) - English
Resource type - Conference proceedings
SCImago Journal Rank - 0.192
H-Index - 176
pISSN - 0277-786X
DOI - 10.1117/12.2582205
Subject(s) - artificial intelligence , segmentation , computer science , surface (topology) , convolutional neural network , computer vision , image segmentation , pixel , pattern recognition (psychology) , image (mathematics) , object (grammar) , deep learning , scale space segmentation , mathematics , geometry
In this paper, we present FlyBy CNN, a novel deep learning based approach for 3D shape segmentation. FlyByCNN consists of sampling the surface of the 3D object from different view points and extracting surface features such as the normal vectors. The generated 2D images are then analyzed via 2D convolutional neural networks such as RUNETs. We test our framework in a dental application for segmentation of intra-oral surfaces. The RUNET is trained for the segmentation task using image pairs of surface features and image labels as ground truth. The resulting labels from each segmented image are put back into the surface thanks to our sampling approach that generates 1-1 correspondence of image pixels and triangles in the surface model. The segmentation task achieved an accuracy of 0.9.