Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning
With the wide application of isometric 3D models, the representation and recognition of them receive increasing attention. Most existing methods for shape representation and analysis either focus on using the constrained hand-craft models or purely devote efforts on developing complicated deep learn...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8886483/ |
id |
doaj-d6cb8fe991684a7c992f460631e1513a |
---|---|
record_format |
Article |
spelling |
doaj-d6cb8fe991684a7c992f460631e1513a2021-03-30T00:19:15ZengIEEEIEEE Access2169-35362019-01-01715850315851310.1109/ACCESS.2019.29502798886483Isometric Shape Representation by Integrating Shape Function Maps and Deep LearningZijian Wang0Zhenzhong Kuang1https://orcid.org/0000-0001-9813-7037Zhiqiang Guo2Suguo Zhu3Min Tan4Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, ChinaKey Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, ChinaKey Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, ChinaKey Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, ChinaKey Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, ChinaWith the wide application of isometric 3D models, the representation and recognition of them receive increasing attention. Most existing methods for shape representation and analysis either focus on using the constrained hand-craft models or purely devote efforts on developing complicated deep learning methods. In order to make full use of the advantages of both, this paper presents a novel mixture modeling approach by integrating both the shape function map (SFM) and the deep convolutional neural network (CNN). First, multiple SFM maps are constructed to grasp the rigid and non-rigid information that are usually considered separately for shape representation. Then, to fully characterize the low-level information existing in SFM, diverse sets of deep features are learned on different SFM maps during the training process of classifiers. Finally, both the rigid and non-rigid deep features are integrated for more discriminative feature abstraction. The experimental results on standard shape benchmark datasets have validated the superior performance of our proposed approach on feature extraction, classification and retrieval. Besides, our evaluation results on extensive shape datasets (e.g. noisy, CAD and protein shapes) have again verified the effectiveness of the proposed algorithm.https://ieeexplore.ieee.org/document/8886483/Shape functionfeature mapisometric shape recognitiondeep learningfeature integration |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zijian Wang Zhenzhong Kuang Zhiqiang Guo Suguo Zhu Min Tan |
spellingShingle |
Zijian Wang Zhenzhong Kuang Zhiqiang Guo Suguo Zhu Min Tan Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning IEEE Access Shape function feature map isometric shape recognition deep learning feature integration |
author_facet |
Zijian Wang Zhenzhong Kuang Zhiqiang Guo Suguo Zhu Min Tan |
author_sort |
Zijian Wang |
title |
Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning |
title_short |
Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning |
title_full |
Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning |
title_fullStr |
Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning |
title_full_unstemmed |
Isometric Shape Representation by Integrating Shape Function Maps and Deep Learning |
title_sort |
isometric shape representation by integrating shape function maps and deep learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
With the wide application of isometric 3D models, the representation and recognition of them receive increasing attention. Most existing methods for shape representation and analysis either focus on using the constrained hand-craft models or purely devote efforts on developing complicated deep learning methods. In order to make full use of the advantages of both, this paper presents a novel mixture modeling approach by integrating both the shape function map (SFM) and the deep convolutional neural network (CNN). First, multiple SFM maps are constructed to grasp the rigid and non-rigid information that are usually considered separately for shape representation. Then, to fully characterize the low-level information existing in SFM, diverse sets of deep features are learned on different SFM maps during the training process of classifiers. Finally, both the rigid and non-rigid deep features are integrated for more discriminative feature abstraction. The experimental results on standard shape benchmark datasets have validated the superior performance of our proposed approach on feature extraction, classification and retrieval. Besides, our evaluation results on extensive shape datasets (e.g. noisy, CAD and protein shapes) have again verified the effectiveness of the proposed algorithm. |
topic |
Shape function feature map isometric shape recognition deep learning feature integration |
url |
https://ieeexplore.ieee.org/document/8886483/ |
work_keys_str_mv |
AT zijianwang isometricshaperepresentationbyintegratingshapefunctionmapsanddeeplearning AT zhenzhongkuang isometricshaperepresentationbyintegratingshapefunctionmapsanddeeplearning AT zhiqiangguo isometricshaperepresentationbyintegratingshapefunctionmapsanddeeplearning AT suguozhu isometricshaperepresentationbyintegratingshapefunctionmapsanddeeplearning AT mintan isometricshaperepresentationbyintegratingshapefunctionmapsanddeeplearning |
_version_ |
1724188489214328832 |