Non-rigid 3D shape classification based on convolutional neural networks

Jan Franco Llerena Quenaya, Cristian José Lopez Del Alamo

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

Over the years, the scientific interest towards 3D models analysis has become more popular. Problems such as classification, retrieval and matching are studied with the idea to offer robust solutions. This paper introduces a 3D object classification method for non-rigid shapes, based on the detection of key points, the use of spectral descriptors and deep learning techniques. We adopt an approach of converting the models into a "spectral image". By extracting interest points and calculating three types of spectral descriptors (HKS, WKS and GISIF), we generate a three-channel input to a convolutional neural network. This CNN is trained to automatically learn features such as topology of 3D models. The results are evaluated and analyzed using the Non-Rigid Classification Benchmark SHREC 2011. Our proposal shows promising results in classification tasks compared to other methods, and also it is robust under several types of transformations.

Idioma originalInglés
Título de la publicación alojada2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-6
Número de páginas6
ISBN (versión digital)9781538637340
DOI
EstadoPublicada - 7 feb. 2018
Publicado de forma externa
Evento2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Arequipa, Perú
Duración: 8 nov. 201710 nov. 2017

Serie de la publicación

Nombre2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017 - Proceedings
Volumen2017-November

Conferencia

Conferencia2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2017
País/TerritorioPerú
CiudadArequipa
Período8/11/1710/11/17

Nota bibliográfica

Publisher Copyright:
© 2017 IEEE.

Huella

Profundice en los temas de investigación de 'Non-rigid 3D shape classification based on convolutional neural networks'. En conjunto forman una huella única.

Citar esto