Deep learning-based image compression for enhanced hyperspectral processing in the protection of stone cultural relics

被引:0
作者
Peng, Lixin [1 ,2 ,4 ]
Bo, Wu [3 ,4 ]
Yang, Haiqing [1 ,2 ]
Li, Xingyue [1 ,2 ]
机构
[1] Chongqing Univ, Sch Civil Engn, Key Lab New Technol Construct Cities Mt Area, Chongqing 400045, Peoples R China
[2] Natl Joint Engn Res Ctr Geohazards Prevent Reservo, Chongqing 400045, Peoples R China
[3] Tibet Univ, Xizang 850032, Peoples R China
[4] Plateau Major Infrastruct Smart Construct & Resili, Xizang 850032, Peoples R China
基金
中国国家自然科学基金;
关键词
Stone cultural heritage; Deterioration identification; Hyperspectral imaging; Image compression; Deep learning; CLASSIFICATION; NETWORK; RATES;
D O I
10.1016/j.eswa.2025.126691
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Compared to the artificial identification of deterioration modes in stone cultural heritage, machine identification is more objective, detailed, accurate, timely, and cost-effective. Hyperspectral data can expand the information dimension and improve machine recognition capabilities. However, this augmentation of information introduces challenges in recognition efficiency, storage, and transmission. To address these challenges, this paper presents a deep learning radial basis function (RBF) compression algorithm, aimed at enhancing the efficacy of hyper- spectral image analysis. The experimental results show that the identification model's F1-score remained around 0.95, with an average improvement in identification accuracy of 1.4%. Overall identification efficiency was enhanced by 13.8%, the identification model's training time was reduced by an average of 4.7%, and the identification time was reduced by an average of 9.1%. It provides a new scheme based on hyperspectral for nondestructive testing of stone cultural relics. And provides the corresponding business support for the relevant units.
引用
收藏
页数:14
相关论文
共 90 条
[41]   Improving performance of spatio-temporal machine learning models using forward feature selection and target-oriented validation [J].
Meyer, Hanna ;
Reudenbach, Christoph ;
Hengl, Tomislav ;
Katurji, Marwan ;
Nauss, Thomas .
ENVIRONMENTAL MODELLING & SOFTWARE, 2018, 101 :1-9
[42]   Deep Architectures for Image Compression: A Critical Review [J].
Mishra, Dipti ;
Singh, Satish Kumar ;
Singh, Rajat Kumar .
SIGNAL PROCESSING, 2022, 191
[43]   PSOWNNs-CNN: A Computational Radiology for Breast Cancer Diagnosis Improvement Based on Image Processing Using Machine Learning Methods [J].
Nomani, Ashkan ;
Ansari, Yasaman ;
Nasirpour, Mohammad Hossein ;
Masoumian, Armin ;
Pour, Ehsan Sadeghi ;
Valizadeh, Amin .
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
[44]   Fast cropping method for proper input size of convolutional neural networks in underwater photography [J].
Park, Jin-Hyun ;
Choi, Young-Kiu ;
Kang, Changgu .
JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY, 2020, 28 (11) :872-881
[45]   Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms [J].
Phillips, P. Jonathon ;
Yates, Amy N. ;
Hu, Ying ;
Hahn, Carina A. ;
Noyes, Eilidh ;
Jackson, Kelsey ;
Cavazos, Jacqueline G. ;
Jeckeln, Geraldine ;
Ranjan, Rajeev ;
Sankaranarayanan, Swami ;
Chen, Jun-Cheng ;
Castillo, Carlos D. ;
Chellappa, Rama ;
White, David ;
O'Toole, Alice J. .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018, 115 (24) :6171-6176
[46]   GuidedNet: A General CNN Fusion Framework via High-Resolution Guidance for Hyperspectral Image Super-Resolution [J].
Ran, Ran ;
Deng, Liang-Jian ;
Jiang, Tai-Xiang ;
Hu, Jin-Fan ;
Chanussot, Jocelyn ;
Vivone, Gemine .
IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (07) :4148-4161
[47]   Calculation of retinal image quality for polychromatic light [J].
Ravikumar, Sowmya ;
Thibos, Larry N. ;
Bradley, Arthur .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2008, 25 (10) :2395-2407
[48]  
Redmon J., 2018, arXiv
[49]   YOLO9000: Better, Faster, Stronger [J].
Redmon, Joseph ;
Farhadi, Ali .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :6517-6525
[50]   Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].
Ren, Shaoqing ;
He, Kaiming ;
Girshick, Ross ;
Sun, Jian .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149