Non-destructive Banana Quality Assessment and Quality and Safety Monitoring using Spectral Imaging Technology

¹ Analysis and Testing Center, Chinese Academy of Tropical Agricultural Sciences/Key Laboratory of Quality and Safety Control for Subtropical Fruit and Vegetable and Laboratory of Quality and Safety Risk Assessment for Tropical Products of Ministry of Agriculture and Rural Affairs, Haikou 571101, China,

ssr 2024 , 6(5), 58–64; https://doi.org/10.26689/ssr.v6i5.6887

Download PDF

Cite

XML

HTML

Abstract

This thesis discusses a method to realize non-destructive banana quality assessment and quality and safety monitoring using spectral imaging technology. As one of the important agricultural products in China, the quality and safety of bananas have always attracted much attention. Traditional quality assessment methods often require destroying bananas, but this method uses spectral imaging technology to realize the assessment of banana quality by measuring and analyzing the spectral characteristics of bananas. At the same time, this method also utilizes spectroscopic technology to detect harmful substances in bananas to realize the safety monitoring of banana quality. The experimental results show that the method has high accuracy and reliability, and can be used as a rapid, efficient, non-destructive means of banana quality assessment and quality and safety monitoring.

References

Jin K, Guo C, Zeng YL, et al., 2023, Hyperspectral Kiwifruit Quality Classification by Combining Three-dimensional Convolutional Neural Network and Haar Wavelet Filter. Advances in Lasers and Optoelectronics, 60(20): 49–58.

Jing XZ, Sun X, Guo YM, et al., 2023, Progress of Spectral Imaging Technology in Maize Seed Quality Inspection. Journal of Northern Agriculture, 51(05): 93–102.

Yuan J, Mao YZ, Yao CP, et al., 2023, Application of Near-infrared Spectroscopy in the Rapid Detection of Saccharification Power of Soy Sauce-type Dacquoise. Brewing Science and Technology, 2023(12): 110–113.

Wen X, 2019, Inversion of Chlorophyll and Nitrogen Content Distribution of Apple Leaves based on Hyperspectral Imaging, thesis, Shandong Agricultural University.

Wang WC, 2023, Corn Mold Detection and Early Warning based on Hyperspectral Imaging Technology, thesis, Liaocheng University.

Cao F, 2019, Research on Rice Origin Identification based on Hyperspectral Imaging Technology, thesis, Jilin Agricultural University.

Hou ML, Pan N, Ma QL, et al., 2017, Research Review of Hyperspectral Imaging Technology in the Analysis of Painted Cultural Relics. Spectroscopy and Spectral Analysis, 37(06): 1852–1860.

He JW, 2016, Research on Non-destructive Detection of Frozen Food Quality based on Hyperspectral Image Technology, thesis, Tianjin University of Commerce.

Zhao LL, Yin ZX, Chen H, et al., 2023, Classification of Angelica sinensis and Dioscorea sinensis based on Hyperspectral Imaging. Automation and Information Engineering, 44(06): 33–38 + 45.

Ning XF, Liu N, Chen YL, et al., 2020, Comparative Study of Spectral Detection Methods for Strawberry Quality. Journal of Shenyang Agricultural University, 51(02): 177–184.

Li SP, Wang JY, Wang L, 2023, Construction and Application of Calibration Model for Straight-Chain Starch Content based on Near-infrared Spectroscopy. Grain and Fats, 36(12): 139–143.

Fan K, 2023, Nitrogen Balance Index Monitoring of Winter Wheat based on Canopy Hyperspectroscopy, thesis, Northwest Agriculture and Forestry University.

Zhao S, Zhao X, Zhu Q, et al., 2022, An Unsupervised Active Learning-based Model Construction Method for Non-destructive Detection of Apple Quality Spectra. Spectroscopy and Spectral Analysis, 42(01): 282–291.

Zhou C, 2016, Research on Feature Extraction and Model Construction Method for Optimal Imaging Hyperspectral of Wheat Leaf Biomass, thesis, Nanjing Agricultural University.

Ni XX, 2015, Identification of Red Acid Branch Species based on Hyperspectral Imaging Technology, thesis, Zhejiang Agriculture and Forestry University.

Previous article in this issue

Next article in this issue