Classification of Fusarium-infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: a comparative analysis

Abstract

Wheat infections caused by fungi of the genus Fusarium decrease yields and have serious economic consequences. The produced mycotoxins have harmful effects on human and animal health. The aim of this study was to develop classification models based on selected textural parameters to distinguish between infected and healthy wheat kernels. The classification accuracy of kernels positioned on the ventral side was determined at 78-100% in the model based on textural parameters from hyperspectral images, and at 95-100% based on images generated by a flatbed scanner. Kernels positioned on the dorsal side were correctly classified in 78-98% based on hyperspectral images, and in 92-100% based on colour images. In the models combining textural parameters from the ventral and dorsal sides of wheat kernels, classification accuracy reached 76-98% in hyperspectral images, and 94-100% in images generated by a flatbed scanner. The imaging technique-flatbed scanner and the ventral side of the kernels provided higher classification accuracy results. The results will contribute to further research aiming to develop models for the determination of fungal chemotypes and/or fungal species based on selected textural features of wheat kernels.

The Application of Computer Image Analysis Based on Textural Features for the Identification of Barley Kernels Infected with Fungi of the Genus Fusarium

“…The classification accuracies noted in this study are similar to those reported by Ropelewska and Zapotoczny (2018) in the classification of infected and healthy wheat kernels. In models containing textural features from the ventral and dorsal sides of kernels, Ropelewska and Zapotoczny (2018) observed classification accuracies in the range of 94-100% for images acquired with a flatbed scanner and 76-98% for hyperspectral images. Jirsa and Polišenska (2011) reported 85% accuracy in infected and healthy wheat kernels classified with the use of a model containing color descriptors.…”

Detection of scab in wheat ears using in situ hyperspectral data and support vector machine optimized by genetic algorithm

“…The scab identification model constructed by support vector machine (SVM) and back propagation neural network achieved excellent results and an accuracy of more than 90%. Ewa et al [8] constructed a classification model based on texture parameters of hyperspectral images to identify infected kernels, and ventral kernels were classified with 100% accuracy. These studies all achieved good results, and they all directly identified the infected or uninfected kernels through hyperspectral technology in the laboratory.…”

Identification of Fusarium Head Blight in Winter Wheat Ears Based on Fisher’s Linear Discriminant Analysis and a Support Vector Machine

“…DON, commonly known as vomitoxin, has acute adverse effects in animals, including food refusal, diarrhea, emesis, alimentary hemorrhaging, and contact dermatitis [4,5]. FHB of wheat not only causes a significant drop in food production, but the DON produced by pathogens also hurts human and animal health, causing food safety problems [6,7]. Therefore, it is important to monitor the health condition of wheat in the field pre-harvest, and to identify the diseased ears.FHB is caused by fungal infection, which affects the normal physiological function of wheat and changes the external morphology and internal physiological structure [8][9][10].…”

“…The constructed linear discriminant analysis SVM and back propagation (BP) neural network models have good success in identifying FHB-infected kernels, with accuracy rates above 90% [13]. Ewa et al (2018) constructed a classification model based on texture parameters of hyperspectral images to identify the infected kernels, and kernels positioned on the ventral side were classified with 100% accuracy [6]. Delwiche et al (2019) used hyperspectral imaging on individual kernels and linear discriminant analysis models to differentiate between healthy and Fusarium-damaged kernels based on the mean reflectance values of the interior pixels of each kernel at four wavelengths (1100, 1197, 1308, and 1394 nm).…”