Detection of Fusarium head blight contamination in wheat kernels by multivariate imaging

Jaillais, Benoît; Roumet, Pierre; Pinson‐Gadais, Laëtitia; Bertrand, Dominique

doi:10.1016/j.foodcont.2015.01.048

Cited by 41 publications

(36 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dammer et al [36] used the wavelengths of 670 and 800 nm for detection of wheat kernels infected with Fusarium. However, Jaillais et al [37] observed that wavelengths of 875 and 950 nm were useful for estimating the degree of wheat kernel contamination by Fusarium and additionally, wavelength of 360 nm was relevant to distinguish between infected and healthy kernels based on shape. The authors could apply another imaging system and kernels infected with another species of the genus Fusarium, which caused other symptoms than in our studies.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Ropelewska

Zapotoczny

2018

Eur Food Res Technol

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Selected Bayes (Bayes Net), Function (LDA), Lazy (K Star), Rules (PART) and Decision Tree (LMT) classifiers were used. The classifiers were tested by tenfold cross-validation [33][34][35][36][37][38][39]. The search method, classifiers and the validation method were selected based on highest classification accuracy.…”

Section: Resultsmentioning

confidence: 99%

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

Ropelewska

Zapotoczny

2018

Eur Food Res Technol

View full text Add to dashboard Cite

show abstract

“…Up to now, research on wheat Fusarium infection was primarily focused on approaches to classify the fungal disease of wheat kernels by grey threshold segmentation, or extract head blight symptoms based on PCA [33][34][35]. In the early development stage of Fusarium head blight disease, infected and healthy grains are easier to separate, but the disease symptoms are difficult to diagnose.…”

Section: Introductionmentioning

confidence: 99%

Classifying Wheat Hyperspectral Pixels of Healthy Heads and Fusarium Head Blight Disease Using a Deep Neural Network in the Wild Field

et al. 2018

View full text Add to dashboard Cite

Classification of healthy and diseased wheat heads in a rapid and non-destructive manner for the early diagnosis of Fusarium head blight disease research is difficult. Our work applies a deep neural network classification algorithm to the pixels of hyperspectral image to accurately discern the disease area. The spectra of hyperspectral image pixels in a manually selected region of interest are preprocessed via mean removal to eliminate interference, due to the time interval and the environment. The generalization of the classification model is considered, and two improvements are made to the model framework. First, the pixel spectra data are reshaped into a two-dimensional data structure for the input layer of a Convolutional Neural Network (CNN). After training two types of CNNs, the assessment shows that a two-dimensional CNN model is more efficient than a one-dimensional CNN. Second, a hybrid neural network with a convolutional layer and bidirectional recurrent layer is reconstructed to improve the generalization of the model. When considering the characteristics of the dataset and models, the confusion matrices that are based on the testing dataset indicate that the classification model is effective for background and disease classification of hyperspectral image pixels. The results of the model show that the two-dimensional convolutional bidirectional gated recurrent unit neural network (2D-CNN-BidGRU) has an F1 score and accuracy of 0.75 and 0.743, respectively, for the total testing dataset. A comparison of all the models shows that the hybrid neural network of 2D-CNN-BidGRU is the best at preventing over-fitting and optimize the generalization. Our results illustrate that the hybrid structure deep neural network is an excellent classification algorithm for healthy and Fusarium head blight diseased classification in the field of hyperspectral imagery.

show abstract

“…Computer-assisted techniques including visible and nearinfrared spectroscopy are more and more frequently used with some success for FHB assessment in the field because of the previously quoted reasons. Multispectral images have been used to detect FHB development in the field (Bauriegel et al 2011;Dammer et al 2011), as well as to detect Fusarium-damaged kernels (Shahin and Symons 2011;Jaillais et al 2015), but trying to predict DON accumulation from spike inspection is quite innovative.…”

Section: Power Of Computer-assisted Image Analysis In the Determinatimentioning

confidence: 99%

Visual assessment and computer–assisted image analysis of Fusarium head blight in the field to predict mycotoxin accumulation in wheat grains

et al. 2017

View full text Add to dashboard Cite

Detection of Fusarium head blight contamination in wheat kernels by multivariate imaging

Cited by 41 publications

References 41 publications

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

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

Classifying Wheat Hyperspectral Pixels of Healthy Heads and Fusarium Head Blight Disease Using a Deep Neural Network in the Wild Field

Visual assessment and computer–assisted image analysis of Fusarium head blight in the field to predict mycotoxin accumulation in wheat grains

Contact Info

Product

Resources

About