Dataset Information

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels.

ABSTRACT: Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography-Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R² of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.

SUBMITTER: Dhakal K

PROVIDER: S-EPMC10098892 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels.

Dhakal Kshitiz K Dhakal Kshitiz K Sivaramakrishnan Upasana U Zhang Xuemei X Belay Kassaye K Oakes Joseph J Wei Xing X Li Song S

Sensors (Basel, Switzerland) 20230328 7

Fusarium head blight (FHB) is a disease of small grains caused by the fungus <i>Fusarium graminearum</i>. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damag ...[more]

PMID: 37050581

Similar Datasets

Project description:Chlorophyll density (ChD) can reflect the photosynthetic capacity of the winter wheat population, therefore achieving real-time non-destructive monitoring of ChD in winter wheat is of great significance for evaluating the growth status of winter wheat. Derivative preprocessing has a wide range of applications in the hyperspectral monitoring of winter wheat chlorophyll. In order to research the role of fractional-order derivative (FOD) in the hyperspectral monitoring model of ChD, this study based on an irrigation experiment of winter wheat to obtain ChD and canopy hyperspectral reflectance. The original spectral reflectance curves were preprocessed using 3 FOD methods: Grünwald-Letnikov (GL), Riemann-Liouville (RL), and Caputo. Hyperspectral monitoring models for winter wheat ChD were constructed using 8 machine learning algorithms, including partial least squares regression, support vector regression, multi-layer perceptron regression, random forest regression, extra-trees regression (ETsR), decision tree regression, K-nearest neighbors regression, and gaussian process regression, based on the full spectrum band and the band selected by competitive adaptive reweighted sampling (CARS). The main results were as follows: For the 3 types of FOD, GL-FOD was suitable for analyzing the change process of the original spectral curve towards the integer-order derivative spectral curve. RL-FOD was suitable for constructing the hyperspectral monitoring model of winter wheat ChD. Caputo-FOD was not suitable for hyperspectral research due to its insensitivity to changes in order. The 3 FOD calculation methods could all improve the correlation between the original spectral curve and Log(ChD) to varying degrees, but only the GL method and RL method could observe the change process of correlation with order changes, and the shorter the wavelength, the smaller the order, and the higher the correlation. The bands screened by CARS were distributed throughout the entire spectral range, but there was a relatively concentrated distribution in the visible light region. Among all models, CARS was used to screen bands based on the 0.3-order RL-FOD spectrum, and the model constructed using ETsR reached the best accuracy and stability. Its R2c, RMSEc, R2v, RMSEv, and RPD were 1.0000, 0.0000, 0.8667, 0.1732, and 2.6660, respectively. In conclusion, based on the winter wheat ChD data set and the corresponding canopy hyperspectral data set, combined with 3 FOD calculation methods, 1 band screening method, and 8 modeling algorithms, this study constructed hyperspectral monitoring models for winter wheat ChD. The results showed that based on the 0.3-order RL-FOD, combined with the CARS screening band, ETsR modeling has the highest accuracy, and hyperspectral estimation of winter wheat ChD can be realized. The results of this study can provide some reference for the rapid and nondestructive estimation of ChD in winter wheat.

Project description:This article presents a dataset of hyperspectral images of handwriting samples collected from 54 individuals. The purpose of the presented dataset is to further explore the use of hyperspectral imaging in document image analysis and to benchmark the performance of forensic analysis methods for hyperspectral document images. Each hyperspectral cube in the dataset has a spatial resolution of 512 × 650 pixels and contains 149 spectral channels in the spectral range of 478-901 nm. All the individuals have different personalities and have their writing patterns. The information of age and gender of each individual is collected. Each subject has written twenty-eight sentences using 12 different varieties of pens from different brands in blue color, each approximately 9 words or 33 characters long, all English alphabets in capital and small cases, digits from 0 to 9. The previous methods use synthetic mixed samples created by joining different parts of the images from the UWA WIHSI dataset.Each document consists of real mixed samples written withdifferent pens and by different writers with a variety of mixing ratios of inks and writers for forensic analysis.The standard A4 pages, each weighing 70 gs and manufactured by "AA" company, are used for data collection. The handwritten notes written by each subject with different pens are annotated in rectangular boxes. This dataset can be used for several tasks related to hyperspectral document image analysis and document forensic analysis including, handwritten optical character recognition, ink mismatch detection, writer identification at sentence, word, and character-level, handwriting-based gender classification, handwriting-based age prediction, handwritten word segmentation, and word generation. This dataset was designed and collected by the research team at the Artificial intelligence and Computer Vision Lab (iVision), Institute of Space Technology, Pakistan, and the hyperspectral images were acquired through imaging spectroscopy in the visible wavelength range at Wageningen University & Research, the Netherlands.

Dataset Information

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels.

Publications

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets