A Machine Learning Method Based on 3D Local Surface Representation for Recognizing the Inscriptions on Ancient Stele

被引:0
作者
Murtala, Sheriff [1 ]
Choi, Ye-Chan [2 ]
Choi, Kang-Sun [1 ,2 ]
机构
[1] Korea Univ Technol & Educ, Future Convergence Engn, Dept Elect Elect & Commun Engn, Cheonan 31253, South Korea
[2] Korea Univ Technol & Educ, Future Convergence Engn, Interdisciplinary Program Creat Engn, Cheonan 31253, South Korea
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 12期
基金
新加坡国家研究基金会;
关键词
spin image; cross spin image; relief extraction; random forest; machine learning; CULTURAL-HERITAGE; RECOGNITION; CURVES;
D O I
10.3390/app11125758
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
It is challenging to extract reliefs from ancient steles due to their rough surfaces, which contain relief-like noise such as dents and scratches. In this paper, we propose a method to segment relief region from 3D scanned ancient stele by exploiting local surface characteristics. For each surface point, four points that are apart from the reference point along the direction of the principal curvatures of the point are identified. The spin images of the reference point and the four relative points are concatenated to provide additional local surface information of the reference point. A random forest model is trained with the local surface features and, thereafter, used to classify 3D surface point as relief or non-relief. To effectively distinguish relief from the degraded surface region containing relief-like noise, the model is trained using three-class labels consisting of relief, background, and degraded surface region. The initial three-class result obtained from the model is refined using the k-nearest neighbors algorithm, and, finally, the degraded region is re-labeled to background region. Experimental results show that the proposed method performed better than the state-of-the-art, SVM-based method with a margin of 0.68%, 3.53%, 2.25%, and 2.36%, in accuracy, precision, F1 score, and SIRI, respectively. When compared with the height- and curvature-based methods, the proposed method outperforms these existing methods with accuracy, precision, F1 score, and SIRI gains of over 4%, 20%, 11%, and 12%, respectively.
引用
收藏
页数:20
相关论文
共 35 条
[1]   Unwrapping and visualizing cuneiform tablets [J].
Anderson, SE ;
Levoy, M .
IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2002, 22 (06) :82-88
[2]  
[Anonymous], 1997, A representation for 3D surface matching
[3]   A machine learning framework for enhancing digital experiences in cultural heritage [J].
Belhi, Abdelhak ;
Bouras, Abdelaziz ;
Al-Ali, Abdulaziz Khalid ;
Foufou, Sebti .
JOURNAL OF ENTERPRISE INFORMATION MANAGEMENT, 2023, 36 (03) :734-746
[4]   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
[5]  
Belongie S, 2001, ADV NEUR IN, V13, P831
[6]  
CAMUFFO D, 1995, SCI TOTAL ENVIRON, V167, P1, DOI 10.1016/0048-9697(95)04565-I
[7]   Angular-partitioned spin image descriptor for robust 3D facial landmark detection [J].
Choi, K. -S. ;
Kim, D. -H. .
ELECTRONICS LETTERS, 2013, 49 (23) :1454-1455
[8]   Relief Extraction From a Rough Stele Surface Using SVM-Based Relief Segment Selection [J].
Choi, Ye-Chan ;
Murtala, Sheriff ;
Jeong, Beom-Chae ;
Choi, Kang-Sun .
IEEE ACCESS, 2021, 9 :4973-4982
[9]  
Cignoni P., 2008, EUR IT CHAPT C, P129, DOI 10.2312/LocalChapterEvents/ItalChap/ItalianChapConf2008/129-136
[10]   Digital image enhancement for recording rupestrian engravings: applications to an alpine rockshelter [J].
Defrasne, Claudia .
JOURNAL OF ARCHAEOLOGICAL SCIENCE, 2014, 50 :31-38