dc.creatorLlerena Quenaya, Jan Franco
dc.creatorLópez Del Alamo, Cristian
dc.date.accessioned2018-11-21T17:24:32Z
dc.date.accessioned2023-06-01T13:53:56Z
dc.date.available2018-11-21T17:24:32Z
dc.date.available2023-06-01T13:53:56Z
dc.date.created2018-11-21T17:24:32Z
dc.date.issued2018-02-08
dc.identifierJ. F. L. Quenaya and C. J. Lopez Del Alamo, "Non-rigid 3D shape classification based on convolutional neural networks," 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI), Arequipa, 2017, pp. 1-6. doi: 10.1109/LA-CCI.2017.8285693 keywords: {convolution;feature extraction;feedforward neural nets;image classification;learning (artificial intelligence);shape recognition;solid modelling;3D object classification;3D models;CNN training;deep learning techniques;nonrigid shapes;Nonrigid 3D shape classification;NonRigid Classification Benchmark SHREC 2011;convolutional neural network;spectral image;Three-dimensional displays;Solid modeling;Shape;Heating systems;Kernel;Computational modeling;Eigenvalues and eigenfunctions}, URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8285693&isnumber=8285668
dc.identifier978-1-5386-3734-0
dc.identifierhttp://repositorio.ulasalle.edu.pe/handle/20.500.12953/32
dc.identifierIEEE Latin American Conference on Computational Intelligence (LA-CCI)
dc.identifier10.1109/LA-CCI.2017.8285693
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/6517201
dc.description.abstractOver 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.
dc.languageeng
dc.publisherUniversidad La Salle
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceUniversidad La Salle
dc.sourceRepositorio institucional - ULASALLE
dc.subjectResearch Subject Categories::TECHNOLOGY
dc.titleNon-rigid 3D shape classification based on convolutional neural networks
dc.typeinfo:eu-repo/semantics/article


Este ítem pertenece a la siguiente institución