Approach for 3D Cultural Relic Classification Based on a Low-Dimensional Descriptor and Unsupervised Learning

被引:7
作者
Gao, Hongjuan [1 ,2 ]
Geng, Guohua [1 ]
Zeng, Sheng [1 ]
机构
[1] Northwest Univ, Sch Informat Sci & Tec nol, Xian 710127, Peoples R China
[2] Ningxia Univ, Xinhua Coll, Yinchuan 750021, Ningxia, Peoples R China
基金
中国国家自然科学基金;
关键词
heat kernel signature; bag-of-words; cultural relic classification; unsupervised learning algorithm; OBJECT RECOGNITION; RETRIEVAL; MODEL;
D O I
10.3390/e22111290
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Computer-aided classification serves as the basis of virtual cultural relic management and display. The majority of the existing cultural relic classification methods require labelling of the samples of the dataset; however, in practical applications, there is often a lack of category labels of samples or an uneven distribution of samples of different categories. To solve this problem, we propose a 3D cultural relic classification method based on a low dimensional descriptor and unsupervised learning. First, the scale-invariant heat kernel signature (Si-HKS) was computed. The heat kernel signature denotes the heat flow of any two vertices across a 3D shape and the heat diffusion propagation is governed by the heat equation. Secondly, the Bag-of-Words (BoW) mechanism was utilized to transform the Si-HKS descriptor into a low-dimensional feature tensor, named a SiHKS-BoW descriptor that is related to entropy. Finally, we applied an unsupervised learning algorithm, called MKDSIF-FCM, to conduct the classification task. A dataset consisting of 3D models from 41 Tang tri-color Hu terracotta Eures was utilized to validate the effectiveness of the proposed method. A series of experiments demonstrated that the SiHKS-BoW descriptor along with the MKDSIF-FCM algorithm showed the best classification accuracy, up to 99.41%, which is a solution for an actual case with the absence of category labels and an uneven distribution of different categories of data. The present work promotes the application of virtual reality in digital projects and enriches the content of digital archaeology.
引用
收藏
页码:1 / 22
页数:22
相关论文
共 50 条
[1]  
Abdelrahman M, 2012, LECT NOTES COMPUT SC, V7583, P22, DOI 10.1007/978-3-642-33863-2_3
[2]  
[Anonymous], PROC CVPR IEEE
[3]  
[Anonymous], 2020, ENTROPY SWITZ, DOI DOI 10.3390/e22080817
[4]  
[Anonymous], 2005, Symposium on geometry processing, DOI DOI 10.5555/1281920.1281953
[5]   Shape matching and object recognition using shape contexts [J].
Belongie, S ;
Malik, J ;
Puzicha, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (04) :509-522
[6]   FCM - THE FUZZY C-MEANS CLUSTERING-ALGORITHM [J].
BEZDEK, JC ;
EHRLICH, R ;
FULL, W .
COMPUTERS & GEOSCIENCES, 1984, 10 (2-3) :191-203
[7]   Retrieval and classification methods for textured 3D models: a comparative study [J].
Biasotti, S. ;
Cerri, A. ;
Aono, M. ;
Ben Hamza, A. ;
Garro, V. ;
Giachetti, A. ;
Giorgi, D. ;
Godil, A. ;
Li, C. ;
Sanada, C. ;
Spagnuolo, M. ;
Tatsuma, A. ;
Velasco-Forero, S. .
VISUAL COMPUTER, 2016, 32 (02) :217-241
[8]   A Gromov-Hausdorff Framework with Diffusion Geometry for Topologically-Robust Non-rigid Shape Matching [J].
Bronstein, Alexander M. ;
Bronstein, Michael M. ;
Kimmel, Ron ;
Mahmoudi, Mona ;
Sapiro, Guillermo .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 89 (2-3) :266-286
[9]   Scale-invariant heat kernel signatures for non-rigid shape recognition [J].
Bronstein, Michael M. ;
Kokkinos, Iasonas .
2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, :1704-1711
[10]   3D shape recognition and retrieval based on multi-modality deep learning [J].
Bu, Shuhui ;
Wang, Lei ;
Han, Pengcheng ;
Liu, Zhenbao ;
Li, Ke .
NEUROCOMPUTING, 2017, 259 :183-193