Location: Crop Genetics and Breeding ResearchTitle: Evaluation and classification of five cereal fungi on culture medium using Visible/Near-Infrared (Vis/NIR) hyperspectral imaging
|LU, YAO - China Agricultural University|
|WANG, WEI - China Agricultural University|
|HUANG, MEIGUI - Nanjing Forestry University|
|CHU, XUAN - Zhongkai University|
|LI, CHUNYANG - Jiangsu Academy Agricultural Sciences|
Submitted to: Infrared Physics and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/17/2020
Publication Date: 1/19/2020
Citation: Lu, Y., Wang, W., Huang, M., Ni, X., Chu, X., Li, C. 2020. Evaluation and classification of five cereal fungi on culture medium using Visible/Near-Infrared (Vis/NIR) hyperspectral imaging. Infrared Physics and Technology. 105:Article 103206. https://doi.org/10.1016/j.infrared.2020.103206.
Interpretive Summary: Recent advancement in the new technology - hyperspectral imaging, as a spectral imaging technique, which can provide both spatial and spectral information simultaneously, has significant advantage over traditional NIR spectroscopic technology in the distribution of the chemical composition of samples. Due to its attractive features like nondestructive detection and high efficiency, hyperspectral imaging has become an important identification tool for detecting infections of fungi and contaminations of mycotoxins of cereals. The purpose of this study was to utilize HSI technique to evaluate the growth stages and then classify the species of the five fungi even during their early development, which is of great significance to timely control the fungal infection or mycotoxin contaminations. Overall results were satisfactory, in which accuracies of A. niger and A. glaucus were both greater than 95.87%. To further differentiate fungal species early, the hyperspectral images of five fungi after one day growth were analyzed, and all five species can be distinguished with an average accuracy of 98.89%. The results demonstrated that visual/near-infrared hyperspectral imaging could be used to evaluate growth characteristics of cereal fungi.
Technical Abstract: In order to detect and identify fungal infection in cereals timely even at its early stage of spore germination and development, a visible/near-infrared hyperspectral imaging (V/NIR HSI) system with a wavelength range between 400 and 1000 nm was utilized to determine fungal growth. Five common cereal fungi, Aspergillus parasiticus, A. flavus, A. glaucus, A. niger and Penicillium sp., were selected and cultivated on Maize Agar medium individually for 6 d, HSI images were captured every 24 h for each fungus. Firstly, to classify the growth days of the five fungi, spectral characteristics were analyzed and principal component analysis (PCA) was performed, from which the growth of each fungus can be roughly divided into four growth stages, i.e., the control group-D1, D2, D3, D4-D6. Then support vector machine (SVM) model of each fungus for inoculation days were established with the first four PCs as inputs. Optimal 7 wavelengths were then selected by successive projection algorithm (SPA) to create corresponding multispectral classification models. Overall results were satisfactory, in which accuracies of A. niger and A. glaucus were both higher than 95.87%. To further differentiate fungal species early, the HSI images of five fungi after one day growth were analyzed, and all five species can be distinguished with an average accuracy of 98.89% and 0.97 for Kappa coefficient using SPA-SVM method. The results demonstrated that V/NIR hyperspectral imaging could be used to evaluate growth characteristics of cereal fungi.