Identification of fungi-contaminated peanuts using hyperspectral imaging technology and joint sparse representation model

Abstract

Peanuts with fungal contamination may contain aflatoxin, a highly carcinogenic substance. We propose the use of hyperspectral imaging to quickly and noninvasively identify fungi-contaminated peanuts. The spectral data and spatial information of hyperspectral images were exploited to improve identification accuracy. In addition, successive projection was adopted to select the bands sensitive to fungal contamination. Furthermore, the joint sparse representation based classification (JSRC), which considers neighboring pixels as belonging to the same class, was adopted, and the support vector machine (SVM) classifier was used for comparison. Experimental results show that JSRC outperforms SVM regarding robustness against random noise and considering pixels at the edge of the peanut kernel. The classification accuracy of JSRC reached 99.2% and 98.8% at pixel scale, at least 98.4% and 96.8% at kernel scale for two peanut varieties, retrieving more accurate and consistent results than SVM. Moreover, fungicontaminated peanuts were correctly marked in both learning and test images.

Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts

“…C, respectively Qi, Jiang, Cui, and Yuan (2019). also investigated the NIR HSI in the same wavelength range as ofQiao et al (2017) by adopting joint sparse representationbased classification and revealed classification accuracy of 99.2% and 98.8% at pixel scale, which is more accurate and consistent than SVM classification technique.…”

“…Qiao, Jiang, Qi, Guo, and Yuan (2017) used short-wave HSI in the wavelength range of 967-2499 nm for the detection of fungal-infected peanuts by nonparametric weighted feature extraction technique. They applied SVM for the classification of infected and healthy peanuts and found pixel-wise overall classification accuracy of 99.13%, 96.72%, and 99.73% for variety A, B, and C, respectively Qi, Jiang, Cui, and Yuan (2019). also investigated the NIR HSI in the same wavelength range as ofQiao et al (2017) by adopting joint sparse representationbased classification and revealed classification accuracy of 99.2% and 98.8% at pixel scale, which is more accurate and consistent than SVM classification technique.…”

Rapid nondestructive detection of peanut varieties and peanut mildew based on hyperspectral imaging and stacked machine learning models

“…The accuracy rate of the training set increases by 6.53-8.95%. Among the four variable selection methods, LightGBM exhibits the best performance, which effectively eliminates the collinearity and redundancy (Qi et al, 2019;Sun et al, 2020;Jin et al, 2022), first of all, this paper classifies peanut seed varieties and mildew, identifies two factors that affect peanut yield, and provides a broader reference for improving the quality of peanut seeds. Secondly, the experimental method studied in this paper adds time parameters, Hamming Loss Log Loss and other evaluation indicators, which makes the efficiency and performance of the model more intuitive.…”

“…( Jin et al., 2022 ) used the spatial spectral features of HSI to classify peanut seeds, and the classification accuracy reached 97.64%. ( Qi et al., 2019 ) used HSI technology and joint sparse representation model to identify fungi contaminated peanuts. ( Sun et al., 2020 ) used HSI technology combined with chemometrics to detect the fat content in peanut kernel.…”

The potential and applicability of infrared spectroscopic methods for the rapid screening and routine analysis of mycotoxins in food crops

“…Corn Fungal infection, FUM, AFLA B 1 (Chu et al, 2020;Chu et al, 2017;Del Fiore et al, 2010;Firrao et al, 2010;Kandpal et al, 2015;Kimuli, Wang, Jiang, et al, 2018;Kimuli, Wang, Lawrence, et al, 2018;Lu et al, 2022;Parrag et al, 2020;Tao et al, 2020;Wang et al, 2014;Williams et al, 2010;Williams et al, 2012;Yang et al, 2020;Zhao et al, 2017;Zhu et al, 2016) Wheat Fungal infection, DON, OTA, ergosterol (Alisaac et al, 2019;Barbedo et al, 2017;Bauriegel et al, 2011;Berman et al, 2007;Dammer et al, 2011;Delwiche et al, 2010;Delwiche et al, 2019;Femenias, Bainotti, et al, 2021;Liang et al, 2020;Nadimi et al, 2021;Ropelewska & Zapotoczny, 2018;Senthilkumar et al, 2016;Shao et al, 2020;Shi et al, 2020;Singh et al, 2012;Singh et al, 2007;Zhao et al, 2020) Rice Fungal infection (Siripatrawan & Makino, 2015;Wu et al, 2020) Oats DON (Tekle et al, 2015) Peanuts Fungal contamination (He et al, 2021;Jiang et al, 2016;Qi et al, 2019;Qiao et al, 2017) Barley DON…”