An Algorithm Based on DAF-Net++ Model for Wood Annual Rings Segmentation
Electronics · 09.07.2023 · 12 (14) · 3009
DOI: 10.3390/electronics12143009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 09.07.2023. Verfasst von Zhedong Ge und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, China, Application of Computed Tomography (CT) Scanning Technology to Damage Detection of Timber Frames of Architectural Heritage, Taishan Scholar Project of Shandong Province, China.
Abstract (Originalsprache)
The semantic segmentation of annual rings is a research topic of interest in wood chronology. To solve the problem of wood annual rings being difficult to segment in dense areas and being greatly affected by defects such as cracks and wormholes, this paper builds a DAF-Net++ model which is based on U-Net whose backbone network is VGG16 and filled with dense jump links, CBAM and DCAM. In this model, VGG16 is used to enhance the extraction ability of image features, dense jump links are used to fuse semantic information of different levels, DCAM provides weighting guidance for shallow features, and CBAM solves the loss of down-sampling information. Taking a Chinese fir wood as the experimental object, 1700 CT images of wood transverse section were obtained by medical CT equipment and 120 of them were randomly selected as the dataset, which was expanded by cropping and rotation, among others. DAF-Net++ was used for training the model and segmentation of the annual rings, and finally the performance of the model was evaluated. The training method is freeze training followed by thaw training, and takes Focal Loss as the loss function, ReLU as the activation function, and Adam as the optimizer. The experimental results show that, in the segmentation of CT images of Chinese fir annual rings, the MIoU of DAF-Net++ is 93.67%, the MPA is 96.76%, the PA is 96.63%, and the Recall is 96.76%. Compared with other semantic segmentation models such as U-Net, U-Net++, DeepLabv3+, etc., DAF-Net++ has better segmentation performance.
Förderung
- Natural Science Foundation of Shandong Province, China
- Application of Computed Tomography (CT) Scanning Technology to Damage Detection of Timber Frames of Architectural Heritage
- Taishan Scholar Project of Shandong Province, China
Zitieren
APA
Ge, Z., Zhang, Z., Shi, L., Liu, S., Gao, Y., Zhou, Y., & Sun, Q. (2023). An Algorithm Based on DAF-Net++ Model for Wood Annual Rings Segmentation. Electronics, 12(14), 3009. https://doi.org/10.3390/electronics12143009
Vancouver
Ge Z, Zhang Z, Shi L, Liu S, Gao Y, Zhou Y, et al. An Algorithm Based on DAF-Net++ Model for Wood Annual Rings Segmentation. Electronics. 2023;12(14):3009. doi:10.3390/electronics12143009
BibTeX
@article{Ge2023,
author = {Ge, Zhedong and Zhang, Ziheng and Shi, Liming and Liu, Shuai and Gao, Yisheng and Zhou, Yucheng and Sun, Qiang},
title = {An Algorithm Based on DAF-Net++ Model for Wood Annual Rings Segmentation},
journal = {Electronics},
year = {2023},
volume = {12},
number = {14},
pages = {3009},
doi = {10.3390/electronics12143009}
}
EUVIMED