scholarly journals Powdery Mildew Caused by Erysiphe cruciferarum on Wild Rocket (Diplotaxis tenuifolia): Hyperspectral Imaging and Machine Learning Modeling for Non-Destructive Disease Detection

Agriculture ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 337
Author(s):  
Catello Pane ◽  
Gelsomina Manganiello ◽  
Nicola Nicastro ◽  
Teodoro Cardi ◽  
Francesco Carotenuto

Wild rocket is a widely cultivated salad crop. Typical signs and symptoms of powdery mildew were observed on leaves of Diplotaxis tenuifolia, likely favored by climatic conditions occurring in a greenhouse. Based on morphological features and molecular analysis, the disease agent was identified as the fungal pathogen Erysiphe cruciferarum. To the best of our knowledge, this is the first report of E. cruciferarum on D. tenuifolia. Moreover, the present study provides a non-destructive high performing digital approach to efficiently detect the disease. Hyperspectral image analysis allowed to characterize the spectral response of wild rocket affected by powdery mildew and the adopted machine-learning approach (a trained Random Forest model with the four most contributory wavelengths falling in the range 403–446 nm) proved to be able to accurately discriminate between healthy and diseased wild rocket leaves. Shifts in the irradiance absorption by chlorophyll a of diseased leaves in the spectrum blue range seems to be at the base of the hyperspectral imaging detection of wild rocket powdery mildew.

2011 ◽  
Vol 29 (No. 6) ◽  
pp. 595-602 ◽  
Author(s):  
Q. Lü ◽  
M.-j. Tang ◽  
J.-r. Cai ◽  
J.-w. Zhao ◽  
S. Vittayapadung

It is necessary to develop a non-destructive technique for kiwifruit quality analysis because the machine injury could lower the quality of fruit and incur economic losses. Bruises are not visible externally owing to the special physical properties of kiwifruit peel.We proposed the hyperspectral imaging technique to inspect the hidden bruises on kiwifruit. The Vis/NIR (408–1117 nm) hyperspectral image data was collected. Multiple optimal wavelength (682, 723, 744, 810, and 852 nm) images were obtained using principal component analysis on the high dimension spectral image data (wavelength range from 600 nm to 900 nm). The bruise regions were extracted from the component images of the five waveband images using RBF-SVM classification. The experimental results showed that the error of hidden bruises detection on fruits by means of hyperspectral imaging was 12.5%. It was concluded that the multiple optimal waveband images could be used to constructs a multispectral detection system for hidden bruises on kiwifruits.


2020 ◽  
Vol 16 (11) ◽  
pp. 155014772096846
Author(s):  
Jing Liu ◽  
Yulong Qiao

Spectral dimensionality reduction is a crucial step for hyperspectral image classification in practical applications. Dimensionality reduction has a strong influence on image classification performance with the problems of strong coupling features and high band correlation. To solve these issues, we propose the Mahalanobis distance–based kernel supervised machine learning framework for spectral dimensionality reduction. With Mahalanobis distance matrix–based dimensional reduction, the coupling relationship between features and the elimination of the scale effect are removed in low-dimensional feature space, which benefits the image classification. The experimental results show that compared with other methods, the proposed algorithm demonstrates the best accuracy and efficiency. The Mahalanobis distance–based multiples kernel learning achieves higher classification accuracy than the Euclidean distance kernel function. Accordingly, the proposed Mahalanobis distance–based kernel supervised machine learning method performs well with respect to the spectral dimensionality reduction in hyperspectral imaging remote sensing.


2018 ◽  
Vol 34 (5) ◽  
pp. 789-798 ◽  
Author(s):  
Yuechun Zhang ◽  
Jun Sun ◽  
Junyan Li ◽  
Xiaohong Wu ◽  
Chunmei Dai

Abstract.In order to ensure that safe and healthy tomatoes can be provided to people, a method for quantitative determination of cadmium content in tomato leaves based on hyperspectral imaging technology was put forward in this study. Tomato leaves with seven cadmium stress gradients were studied. Hyperspectral images of all samples were firstly acquired by the hyperspectral imaging system, then the spectral data were extracted from the hyperspectral images. To simplify the model, three algorithms of competitive adaptive reweighted sampling (CARS), variable combination population analysis (VCPA) and bootstrapping soft shrinkage (BOSS) were used to select the feature wavelengths ranging from 431 to 962 nm. Final results showed that BOSS can improve prediction performance and greatly reduce features when compared with the other two selection methods. The BOSS model got the best accuracy in calibration and prediction with R2c of 0.9907 and RMSEC of 0.4257mg/kg, R2p of 0.9821, and RMSEP of 0.6461 mg/kg. Hence, the method of hyperspectral technology combined with the BOSS feature selection is feasible for detecting the cadmium content of tomato leaves, which can potentially provide a new method and thought for cadmium content detection of other crops. Keywords: Feature selection, Hyperspectral image technology, Non-destructive analysis, Regression model, Tomato leaves.


Sensors ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 97 ◽  
Author(s):  
Siddharth Chaudhary ◽  
Sarawut Ninsawat ◽  
Tai Nakamura

The aim of this study was to investigate the potential of the non-destructive hyperspectral imaging system (HSI) and accuracy of the model developed using Support Vector Machine (SVM) for determining trace detection of explosives. Raman spectroscopy has been used in similar studies, but no study has been published which is based on measurement of reflectance from hyperspectral sensor for trace detection of explosives. HSI used in this study has an advantage over existing techniques due to its combination of imaging system and spectroscopy, along with being contactless and non-destructive in nature. Hyperspectral images of the chemical were collected using the BaySpec hyperspectral sensor which operated in the spectral range of 400–1000 nm (144 bands). Image processing was applied on the acquired hyperspectral image to select the region of interest (ROI) and to extract the spectral reflectance of the chemicals which were stored as spectral library. Principal Component Analysis (PCA) and first derivative was applied to reduce the high dimensionality of the image and to determine the optimal wavelengths between 400 and 1000 nm. In total, 22 out of 144 wavelengths were selected by analysing the loadings of principal components (PC). SVM was used to develop the classification model. SVM model established on the whole spectrum from 400 to 1000 nm achieved an accuracy of 81.11%, whereas an accuracy of 77.17% with less computational load was achieved when SVM model was established on the optimal wavelengths selected. The results of the study demonstrate that the hyperspectral imaging system along with SVM is a promising tool for trace detection of explosives.


Plant Disease ◽  
2007 ◽  
Vol 91 (4) ◽  
pp. 461-461 ◽  
Author(s):  
R. Raid ◽  
C. Miller ◽  
K. Pernezny

Parsley (Petroselinum crispum (Mill.) Nym. ex A.W. Hill) is an important leaf crop in the Everglades Agricultural Area of southern Florida. During the spring of 2005 and 2006, disease signs and symptoms resembling those incited by powdery mildew were observed on parsley at a commercial vegetable farm located 15 km east of Belle Glade. Symptoms consisted of leaf chlorosis, particularly in the dense lower canopy, and desiccation of affected tissue. A dense, white-to-light gray fungal growth was visible macroscopically on the surface of affected leaf tissue. Microscopic examinations revealed ectophytic hyphae with lobed appressoria and hyaline, straight conidiophores bearing single conidia. Conidia were short-cylindrical to cylindrical, measured 33 to 44 μm long and 13 to 16 μm wide, and lacked fibrosin bodies. Conidiophore foot cells were also cylindrical, straight, and measured 27 to 37 × 9 to 10 μm. Ascocarps of the teleomorph were not observed. The fungus closely matched the description of Erysiphe heraclei DC, a pathogen previously reported as attacking parsley on the U.S. West Coast (1,2). Pathogenicity was verified by inoculating adaxial leaf surfaces of 12 plants (cv. Dark Green Italian) with conidia collected from infected tissue by using a small brush. Inoculated plants and 12 noninoculated plants were lightly misted, held in a moist chamber for 48 h (22°C), and then incubated in a growth chamber for 4 weeks at 22°C with a photoperiod of 16 h. Symptoms that developed on inoculated plants were similar to those observed in the field, with no symptoms evident on the controls treated in a similar manner. To our knowledge, this is the first report of powdery mildew on parsley in Florida, even though parsley has been grown in the area for at least six decades. Noted as being somewhat unique among fungal pathogens because it favors dry rather than moist climatic conditions, it is probably no coincidence that powdery mildew was observed both years during the month of April, the height of Florida's dry season. The fact that monthly rainfall totals of 22 and 35 mm were recorded during April of 2004 and 2005, respectfully, well below the historical average of 72 mm, may have been a contributing influence. Glawe et al. (1), in issuing a first report of E. heraclei on carrots and parsley in the state of Washington and observing ascocarps on carrot tissue, mentioned the prospect of contaminated seed serving as a potential source of dissemination. Although they did not observe the teleomorph on parsley, prospects for its occurrence seem likely. With the bulk of parsley seed planted in Florida being produced in Washington, Oregon, or California, the observations reported herein may provide credence to such a hypothesis. References: (1) D. A. Glawe et al. Online publication. doi:10.1094/PHP-2005-0114-01-HN. Plant Health Progress, 2005. (2) S. T. Koike and G. S. Saenz. Plant Dis. 78:1219, 1994.


2021 ◽  
Vol 14 (1) ◽  
pp. 84
Author(s):  
Catello Pane ◽  
Gelsomina Manganiello ◽  
Nicola Nicastro ◽  
Francesco Carotenuto

Fusarium oxysporum f. sp. raphani is responsible for wilting wild rocket (Diplotaxis tenuifolia L. [D.C.]). A machine learning model based on hyperspectral data was constructed to monitor disease progression. Thus, pathogenesis after artificial inoculation was monitored over a 15-day period by symptom assessment, qPCR pathogen quantification, and hyperspectral imaging. The host colonization by a pathogen evolved accordingly with symptoms as confirmed by qPCR. Spectral data showed differences as early as 5-day post infection and 12 hypespectral vegetation indices were selected to follow disease development. The hyperspectral dataset was used to feed the XGBoost machine learning algorithm with the aim of developing a model that discriminates between healthy and infected plants during the time. The multiple cross-prediction strategy of the pixel-level models was able to detect hyperspectral disease profiles with an average accuracy of 0.8. For healthy pixel detection, the mean Precision value was 0.78, the Recall was 0.88, and the F1 Score was 0.82. For infected pixel detection, the average evaluation metrics were Precision: 0.73, Recall: 0.57, and F1 Score: 0.63. Machine learning paves the way for automatic early detection of infected plants, even a few days after infection.


NIR news ◽  
2020 ◽  
Vol 31 (5-6) ◽  
pp. 8-14
Author(s):  
José Manuel Amigo

First of all, I want to transmit my most humble thanks to all people who believe that I deserve the “2019 Thomas Hirschfeld” award (kindly supported by FOSS) for my work on near-infrared spectroscopy and, especially, applied on hyperspectral images. I must confess that this award caught me by surprise and that I felt a bit overwhelmed when I received it. It is an honour full of respect and responsibility. I have been given the opportunity of writing this article, and I will profit it to express different personal thoughts about general but relevant aspects of near infrared applied to hyperspectral imaging. Also, since I am more a practitioner in chemometrics (or machine learning or data mining, or …) than a developer, I will also include some insights about the beautiful combination of near-infrared hyperspectral image with chemometrics. This article is just a glimpse of constructive criticism with personal thoughts that comes from my little experience in this field. Therefore, and of course, all opinions here are open for constructive discussion with the only purpose of learning (like the machines do nowadays).


2019 ◽  
Vol 9 (17) ◽  
pp. 3591 ◽  
Author(s):  
Miaole Hou ◽  
Ning Cao ◽  
Li Tan ◽  
Shuqiang Lyu ◽  
Pingping Zhou ◽  
...  

Changes in the environment and human activities can cause serious deterioration of murals. Hyperspectral imaging technology can observe murals in the range of visible to near infrared light, providing a scientific and non-destructive way for mural digital preservation. An effective method to extract hidden information from the sootiness of murals in order to enhance the visual value of patterns in ancient murals using hyperspectral imaging is proposed in this paper. Firstly, Minimum Noise Fraction transform was applied to reduce sootiness features in the background of the mural. Secondly, analysis of spectral characteristics and image subtraction were used to achieve feature enhancement of the murals. Finally, density slicing was performed to extract the patterns under the sootiness. The results showed that the extraction of hidden information was achieved with an overall accuracy of 88.97%.


2021 ◽  
Vol 13 (13) ◽  
pp. 2536
Author(s):  
Sara Freitas ◽  
Hugo Silva ◽  
Eduardo Silva

This paper addresses the development of a remote hyperspectral imaging system for detection and characterization of marine litter concentrations in an oceanic environment. The work performed in this paper is the following: (i) an in-situ characterization was conducted in an outdoor laboratory environment with the hyperspectral imaging system to obtain the spatial and spectral response of a batch of marine litter samples; (ii) a real dataset hyperspectral image acquisition was performed using manned and unmanned aerial platforms, of artificial targets composed of the material analyzed in the laboratory; (iii) comparison of the results (spatial and spectral response) obtained in laboratory conditions with the remote observation data acquired during the dataset flights; (iv) implementation of two different supervised machine learning methods, namely Random Forest (RF) and Support Vector Machines (SVM), for marine litter artificial target detection based on previous training. Obtained results show a marine litter automated detection capability with a 70–80% precision rate of detection in all three targets, compared to ground-truth pixels, as well as recall rates over 50%.


Sign in / Sign up

Export Citation Format

Share Document