Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 26;14(1):7209.
doi: 10.1038/s41598-024-57904-3.

Fully connected-convolutional (FC-CNN) neural network based on hyperspectral images for rapid identification of P. ginseng growth years

Xingfeng Chen  1   2 , Hejuan Du  3 , Yun Liu  4 , Tingting Shi  5 , Jiaguo Li  1 , Jun Liu  1 , Limin Zhao  1 , Shu Liu  6
Affiliations

Fully connected-convolutional (FC-CNN) neural network based on hyperspectral images for rapid identification of P. ginseng growth years

Xingfeng Chen et al. Sci Rep. .

Erratum in

Abstract

P. ginseng is a precious traditional Chinese functional food, which is used for both medicinal and food purposes, and has various effects such as immunomodulation, anti-tumor and anti-oxidation. The growth year of P. ginseng has an important impact on its medicinal and economic values. Fast and nondestructive identification of the growth year of P. ginseng is crucial for its quality evaluation. In this paper, we propose a FC-CNN network that incorporates spectral and spatial features of hyperspectral images to characterize P. ginseng from different growth years. The importance ranking of the spectra was obtained using the random forest method for optimal band selection. Based on the hyperspectral reflectance data of P. ginseng after radiometric calibration and the images of the best five VNIR bands and five SWIR bands selected, the year-by-year identification of P. ginseng age and its identification experiments for food and medicinal purposes were conducted, and the FC-CNN network and its FCNN and CNN branch networks were tested and compared in terms of their effectiveness in the identification of P. ginseng growth years. It has been experimentally verified that the best year-by-year recognition was achieved by utilizing images from five visible and near-infrared important bands and all spectral curves, and the recognition accuracy of food and medicinal use reached 100%. The FC-CNN network is significantly better than its branching model in the effect of edible and medicinal identification. The results show that for P. ginseng growth year identification, VNIR images have much more useful information than SWIR images. Meanwhile, the FC-CNN network utilizing the spectral and spatial features of hyperspectral images is an effective method for the identification of P. ginseng growth year.

Keywords: P. ginseng; FC-CNN; Hyperspectral images; Identification; Spectral importance.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
A system of methods for identifying the year of P. ginseng growth.
Figure 2
Figure 2
The architecture of FC-CNN network. ReLU is the activation layer. BN is a batch normalization layer. DP is the dropout layer. FC is the full connected layer. The input vector possessed N features. Nn is the neutron number of every FC layer, which could be different. Softmax is the special activation function for s classification network.
Figure 3
Figure 3
Spectral curves of P. ginseng samples plotted year by year.
Figure 4
Figure 4
The importance of each band in 10 experiments. The color of the curve in the figure represents the number of randomized trials.
Figure 5
Figure 5
Confusion matrix results for 10 randomized trials of Test 1.
Figure 5
Figure 5
Confusion matrix results for 10 randomized trials of Test 1.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Woo Y, Cho C, Kim H, Yang J, Seong K. Classification of cultivation area of ginseng by near infrared spectroscopy and ICP-AES. Microchem. J. 2002;73:299–306. doi: 10.1016/S0026-265X(02)00094-2. - DOI
    1. Ang-Lee MK, Moss J, Yuan C-S. Herbal medicines and perioperative care. Jama. 2001;286:208–216. doi: 10.1001/jama.286.2.208. - DOI - PubMed
    1. Attele AS, Wu JA, Yuan C-S. Ginseng pharmacology: Multiple constituents and multiple actions. Biochem. Pharmacol. 1999;58:1685–1693. doi: 10.1016/S0006-2952(99)00212-9. - DOI - PubMed
    1. Christensen LP, Jensen M, Kidmose U. Simultaneous determination of ginsenosides and polyacetylenes in American ginseng root (Panax Quinquefolium L.) by high-performance liquid chromatography. J. Agric. Food Chem. 2006;54:8995–9003. doi: 10.1021/jf062068p. - DOI - PubMed
    1. Dai Y-L, et al. Comparing eight types of ginsenosides in ginseng of Different plant ages and regions using RRLC-Q-TOF MS/MS. J. Ginseng Res. 2020;44:205–214. doi: 10.1016/j.jgr.2017.11.001. - DOI - PMC - PubMed