基于高光谱图像波段融合的猕猴桃软腐病早期分类检测

doi:10.3964/j.issn.1000-0593(2024)01-0241-09

Abstract
References
Related Citation (15)

Download: PDF (14992 KB)
Export: BibTeX | EndNote (RIS)

Abstract Kiwifruit soft rot is the most serious fungal disease in the kiwifruit postharvest storage and sales process. It has a long incubation period, and it is difficult to classify it by manual screening when it does not show obvious symptoms in the early stage of infection. Therefore, hyperspectral imaging technology (470～900 nm) was used to study the early detection and identification of kiwifruit soft rot. In the experiment, 295 hyperspectral images of healthy kiwifruit and early and late kiwifruit infected with soft rot were collected, and the samples were divided into training set and test set samples according to 7: 3 by Kennard stone algorithm. Firstly, the region of interest of the samples was selected, and then the average spectrum of the region was taken as the original spectral curve of the sample. Principal component analysis(PCA), successive projections algorithm (SPA) and competitive adaptive reweighting sampling algorithm(CARS) were used to extract spectral features from original spectral curves. Secondly, non subsampled contourlet transform (NSCT) was used for band fusion of the 8 feature bands in the SPA solution process to obtain the fusion image, and then gray level co-occurrence matrix method (GLCM) was used to extract the texture features of the fusion image. Finally, the spectral features and texture features were fused, and the nearest neighbor algorithm (KNN), random forest (RF) and support vector machine(SVM) classification models were established respectively for the early classification and detection of kiwifruit soft rot. In addition, this paper also compares with the texture features extracted from principal component images or feature bands in other literatures. The main innovation of this paper is using NSCT to fuse the feature band images and then extract the texture features, which not only reduces the feature dimension and feature redundancy, but also integrates the complementary information of different band images to improve the classification accuracy. The experimental results show that SVM is the most suitable classifier for this study, and the classification results using spectral features or texture features alone are not satisfactory. However, the classification accuracy can reach 92.05% after the fusion of the two features. Most of the early samples of kiwifruit soft rot have been correctly identified, which indicated that the fusion of the two features obtained the different information of spectrum and image in hyperspectral images. It embodies the “spatial spectral unity” of hyperspectral images. In this study, a rapid and accurate non-destructive test was carried out on kiwifruit at the early stage of soft rot, which could provide some reference and guiding significance for the quality classification of kiwifruit after harvest.

Key words：Kiwifruit soft rot; Hyperspectral image; Band fusion; Spatial spectral unity; Non-destructive testing

Received: 2022-06-11 Accepted: 2022-10-20

ZTFLH:

TP391.4

Corresponding Authors: GUO Zhi-qiang E-mail: guozhiqiang@whut.edu.cn

Cite this article:

GAO Hong-sheng,GUO Zhi-qiang,ZENG Yun-liu, et al. Early Classification and Detection of Kiwifruit Soft Rot Based on Hyperspectral Image Band Fusion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 241-249.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)01-0241-09 OR https://www.gpxygpfx.com/EN/Y2024/V44/I01/241

[1] LI Li, PAN Hui, DENG Lei, et al(李黎，潘慧，邓蕾，等). China Fruits(中国果树), 2020, 206(6): 1.
[2] WANG Yu-mei, GUO Shu-jie(王玉梅，郭淑杰). Scientific and Technological Innovation(科学技术创新), 2018, 15: 164.
[3] HE Fu-xian, MENG Qing-hua, TANG Liu, et al(何馥娴，蒙庆华，唐柳，等). Journal of Fruit Science(果树学报), 2021, 38(9): 1590.
[4] SHEN Ya-qi, LI Song-lin, HE Jie, et al(申亚其，李松林，何杰，等). Forestry Machinery & Woodworking Equipment(林业机械与木工设备), 2021, 49(3): 4.
[5] HU Yi-lei, JIANG Hong-zhe, ZHOU Hong-ping, et al(胡逸磊，姜洪喆，周宏平，等). Science and Technology of Food Industry(食品工业科技), 2021, 42(20): 377.
[6] YANG Jie-kai, GUO Zhi-qiang, HUANG Yuan(杨杰锴，郭志强，黄远). Laser & Optoelectronics Progress(激光与光电子学进展), 2022, 59(10): 23.
[7] LEI Yu, HU Xin-jun, JIANG Mao-lin, et al(雷裕，胡新军，蒋茂林，等). Journal of Food Safety & Quality(食品安全质量检测学报), 2021, 12(21): 8404.
[8] Sun Y, Wei K L, Liu Q, et al. Sensors, 2018, 18(4): 1295.
[9] Yu D M, Xu T Y, Song K. Spectroscopy Letters, 2018, 51(4): 191.
[10] Siedliiska A, Baranowski P, Zubik M, et al. Postharvest Biology and Technology, 2018, 139: 115.
[11] Pan T T, Chyngyz E, Sun D W, et al. Postharvest Biology and Technology, 2019, 154: 96.
[12] Huang Y P, Wang D Z, Liu Y, et al. Sensors, 2020, 20(20): 5783.
[13] Xie C Q, Lee W S. Postharvest Biology and Technology, 2021, 180: 111627.
[14] LIU Si-jia, TIAN You-wen, ZHANG Fang, et al(刘思伽，田有文，张芳，等). Food Science(食品科学), 2017, 38(8): 277.
[15] DONG Jin-lei, GUO Wen-chuan(董金磊，郭文川). Food Science(食品科学) , 2015, 36(16): 101.
[16] GE Yong-hui, SONG Jin, PAN Lei-qing, et al(戈永慧，宋进，潘磊庆，等). Journal of Nanjing Agricultural University(南京农业大学学报), 2022, 45(2): 386.
[17] MENG Qing-long, HUANG Ren-shuai, ZHANG Yan, et al(孟庆龙，黄人帅，张艳，等). Farm Products Processing(农产品加工), 2022，553(11): 66.
[18] SHANG Jing, HUANG Ren-shuai, ZHANG Yan, et al(尚静，黄人帅，张艳，等). Journal of Chinese Agricultural Mechanization(中国农机化学报), 2022, 43(8): 90.
[19] OUYANG Ai-guo, LIU Hao-chen, CHENG Long, et al(欧阳爱国，刘昊辰，成龙，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析) , 2021, 41(8): 2598.
[20] ZHANG Hui, ZHANG Wen-wei, ZHANG Yong-yi, et al(张慧，张文伟，张永毅，等). Acta Tabacaria Sinica(中国烟草学报), 2022, 28(3): 72.