Wheat FHB resistance assessment using hyperspectral feature band image fusion and deep learning

Kun Liang, Zhizhou Ren, Jinpeng Song, Rui Yuan, Qun Zhang

Abstract


The breeding and selection of resistant varieties is an effective way to minimize wheat Fusarium head blight (FHB) hazards, so it is important to identify and evaluate resistant varieties. The traditional resistance phenotype identification is still largely dependent on time-consuming manual methods. In this paper, the method for evaluating FHB resistance in wheat ears was optimized based on the fusion feature wavelength images of the hyperspectral imaging system and the Faster R-CNN algorithm. The spectral data from 400-1000 nm were preprocessed by the multiple scattering correction (MSC) algorithm. Three feature wavelengths (553 nm, 682 nm and 714 nm) were selected by analyzing the X-loading weights (XLW) according to the absolute value of the peaks and troughs in different principal component (PC) load coefficient curves. Then, the different fusion methods of the three feature wavelengths were explored with different weight coefficients. Faster R-CNN was trained on the fusion and RGB datasets with VGG16, AlexNet, ZFNet, and ResNet-50 networks separately. Then, the other detection models SSD, YOLOv5, YOLOv7, CenterNet, and RetinaNet were used to compare with the Faster R-CNN model. As a result, the Faster R-CNN with VGG16 was best with the mAP (mean Average Precision) ranged from 97.7% to 98.8%. The model showed the best performance for the Fusion Image-1 dataset. Moreover, the Faster R-CNN model with VGG16 achieved an average detection accuracy of 99.00%, which was 23.89%, 1.21%, 0.75%, 0.62%, and 8.46% higher than SSD, YOLOv5, YOLOv7, CenterNet, and RetinaNet models. Therefore, it was demonstrated that the Faster R-CNN model based on the hyperspectral feature image fusion dataset proposed in this paper was feasible for rapid evaluation of wheat FHB resistance. This study provided an important detection method for ensuring wheat food security.
Key words: Fusariumhead blight, resistance evaluation, hyperspectral feature band image fusion, deep learning, Faster R-CNN
DOI: 10.25165/j.ijabe.20241702.8269

Citation: Liang K, Ren Z Z, Song J P, Yuan R, Zhang Q. Wheat FHB resistance assessment using hyperspectral feature bandimage fusion and deep learning. Int J Agric & Biol Eng, 2024; 17(2): 240–249.

Keywords


Fusariumhead blight, resistance evaluation, hyperspectral feature band image fusion, deep learning, Faster R-CNN

Full Text:

PDF

References


Wegulo S N, Baenziger P S, Nopsa J H, Bockus W W, Hallen-Adams H. Management of Fusarium head blight of wheat and barley. Crop Protection, 2015; 73: 100–107.

Zhu Z W, Hao Y F, Mergoum M, Bai G H, Humphreys G, Cloutier S, et al. Breeding wheat for resistance to Fusarium head blight in the Global North: China, USA, and Canada. The Crop Journal, 2019; 7(6): 730–738.

Li T, Zhang H J, Huang Y W, Su Z Q, Deng Y, Liu H W, et al. Effects of the Fhb1 gene on Fusarium head blight resistance and agronomic traits of winter wheat. The Crop Journal, 2019; 7(6): 799–808.

Giancaspro A, Lionetti V, Giove S L, Zito D, Fabri E, Reem N, et al. Cell wall features transferred from common into durum wheat to improve Fusarium Head Blight resistance. Plant Science, 2018; 274: 121–128.

Bauriegel E, Giebel A, Geyer M, Schmidt U, Herppich W B. Early detection of Fusarium infection in wheat using hyper-spectral imaging. Computers and Electronics in Agriculture, 2011; 75(2): 304–312.

Landschoot S, Waegeman W, Audenaert K, Van Damme P, Vandepitte J, De Baets B, et al. A field-specific web tool for the prediction of Fusarium head blight and deoxynivalenol content in Belgium. Computers and Electronics in Agriculture, 2013; 93: 140–148.

Palacios S A, Erazo J G, Ciasca B, Lattanzio V M T, Reynoso M M, Farnochi M C, et al. Occurrence of deoxynivalenol and deoxynivalenol-3-glucoside in durum wheat from Argentina. Food Chemistry, 2017; 230: 728–734.

Peiris K H S, Dong Y H, Davis M A, Bockus W W, Dowell F E. Estimation of the deoxynivalenol and moisture contents of bulk wheat grain samples by FT-NIR spectroscopy. Cereal Chemistry, 2017; 94(4): 677–682.

Visconti A, Pascale M. An overview on Fusarium mycotoxins in the durum wheat pasta production chain. Cereal Chemistry, 2010; 87(1): 21–27.

Pestka J J, Smolinski A T. Deoxynivalenol: toxicology and potential effects on humans. Journal of Toxicology and Environmental Health Part B, 2005; 8(1): 39–69.

Ma Y Y, Guo H W. Mini-review of studies on the carcinogenicity of deoxynivalenol. Environmental Toxicology and Pharmacology, 2008; 25(1): 1–9.

Steiner B, Buerstmayr M, Michel S, Schweiger W, Lemmens M, Buerstmayr H. Breeding strategies and advances in line selection for Fusarium head blight resistance in wheat. Tropical Plant Pathology, 2017; 42: 165–174.

Jennings P, Köhl J, Gosman N. Control of mycotoxins: raw material production. In: Magan N, Olsen M. (Eds. ), Mycotoxins in Food. Sawston: Woodhead Publishing. 2004; pp.443–460.

Su Z Q, Jin S J, Zhang D D, Bai G H. Development and validation of diagnostic markers for Fhb1 region, a major QTL for Fusarium head blight resistance in wheat. Theoretical and Applied Genetics, 2018; 131: 2371–2380.

Mesterházy A. Types and components of resistance to Fusarium head blight of wheat. Plant Breeding, 1995; 114(5): 377–386.

Manavalan, R. Automatic identification of diseases in grains crops through computational approaches: A review. Computers and Electronics in Agriculture, 2020; 178: 105802.

Bai G H, Shaner G. Management and resistance in wheat and barley to Fusarium head blight. Annual Review of Phytopathology, 2004; 42: 135–161.

Shete S, Srinivasan S, Gonsalves T A. TasselGAN: An application of the generative adversarial model for creating field-based maize tassel data. Plant Phenomics, 2020; 2020: 8309605.

David E, Madec S, Sadeghi-Tehran P, Aasen H, Zheng B Y, Liu S Y, et al. Global wheat head detection (GWHD) dataset: A large and diverse dataset of high-resolution RGB-Labelled images to develop and benchmark wheat head detection methods. Plant Phenomics, 2020; 2020: 3521852 .

Almoujahed M B, Rangarajan A K, Whetton R L, Vincke D, Eylenbosch D, Vermeulen P, et al. Detection of fusarium head blight in wheat under field conditions using a hyperspectral camera and machine learning. Computers and Electronics in Agriculture, 2022; 203: 107456.

Zhao T X, Chen M, Jiang X S, Shen F, He X M, Fang Y, et al. Integration of spectra and image features of Vis/NIR hyperspectral imaging for prediction of deoxynivalenol contamination in whole wheat flour. Infrared Physics and Technology, 2020; 109: 103426.

Vincke D, Eylenbosch D, Jacquemin G, Chandelier A, Pierna J A F, Stevens F, et al. Near infrared hyperspectral imaging method to assess Fusarium Head Blight infection on winter wheat ears. Microchemical Journal, 2023; 191: 108812.

Zhang N, Pan Y C, Feng H K, Zhao X Q, Yang X D, Ding C L, et al. Development of Fusarium head blight classification index using hyperspectral microscopy images of winter wheat spikelets. Biosystems Engineering, 2019; 186: 83–99.

Zhang D-Y, Chen G, Yin X, Hu R J, Gu C-Y, Pan Z G, et al. Integrating spectral and image data to detect Fusarium head blight of wheat. Computers and Electronics in Agriculture, 2020; 175: 105588.

Gao C F, Guo W, Yang C H, Gong Z, Yue J B, Fu Y Y, et al. A fast and lightweight detection model for wheat fusarium head blight spikes in natural environments. Computers and Electronics in Agriculture, 2024; 216: 108484.

Moghimi A, Yang C, Anderson J A. Aerial hyperspectral imagery and deep neural networks for high-throughput yield phenotyping in wheat. Computers and Electronics in Agriculture, 2020; 172: 105299.

Ren S Q, He K M, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017; 39(6): 1137–1149.

Quan L Z, Feng H Q, Lv Y J, Wang Q, Zhang C B, Liu J G, et al. Maize seedling detection under different growth stages and complex field environments based on an improved Faster R–CNN. Biosystems Engineering, 2019; 184: 1–23.

Ozguven M M, Adem K. Automatic detection and classification of leaf spot disease in sugar beet using deep learning algorithms. Physica A: Statistical Mechanics and its Applications, 2019; 535: 122537.

Wu W, Yang T-l, Li R, Chen C, Liu T, Zhou K, et al. Detection and enumeration of wheat grains based on a deep learning method under various scenarios and scales. Journal of Integrative Agriculture, 2020; 19(8): 1998–2008.

Yang D, Zhou Y X, Jie Y, Li Q Q, Shi T Y. Non-destructive detection of defective maize kernels using hyperspectral imaging and convolutional neural network with attention module. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024; 313: 124166.

Li J M, Yang Z H, Zhao Y R, Yu K Q. HSI combined with CNN model detection of heavy metal Cu stress levels in apple rootstocks. Microchemical Journal, 2023; 194: 109306.

Zhang D Y, Luo H S, Cheng T, Li W F, Zhou X G, Gu C Y, et al. Enhancing wheat Fusarium head blight detection using rotation Yolo wheat detection network and simple spatial attention network. Computers and Electronics in Agriculture, 2023; 211: 107968.

Yu X J, Lu H D, Liu Q Y. Deep-learning-based regression model and hyperspectral imaging for rapid detection of nitrogen concentration in oilseed rape (Brassica napus L.) leaf. Chemometrics and Intelligent Laboratory Systems, 2018; 172: 188–193.

Jin X, Jie L, Wang S, Qi H J, Li S W. Classifying wheat hyperspectral pixels of healthy heads and Fusarium head blight disease using a deep neural network in the wild field. Remote Sensing, 2018; 10(3): 395.

Rehman T U, Ma D D, Wang L J, Zhang L B, Jin J. Predictive spectral analysis using an end-to-end deep model from hyperspectral images for high-throughput plant phenotyping. Computers and Electronics in Agriculture, 2020; 177: 105713.

Zhang P P, Guo C J, Liu Z, Bernardo A, Ma H X, Jiang P, et al. Quantitative trait loci for Fusarium head blight resistance in wheat cultivars Yangmai 38 and Zhengmai 9023. The Crop Journal, 2020; 9(1): 143–153.

Guo J, Zhang X L, Hou Y L, Cai J J, Shen X R, Zhou T T, et al. High-density mapping of the major FHB resistance gene Fhb7 derived from Thinopyrum ponticum and its pyramiding with Fhb1 by marker-assisted selection. Theoretical and Applied Genetics, 2015; 128: 2301–2316.

Isebaert S, Saeger S D, Devreese R, Verhoeven R, Maene P, Heremans B, Haesaert G. Mycotoxin-producing fusarium species occurring in winter wheat in belgium (Flanders) during 2002-2005. Journal of Phytopathology, 2009; 157(2): 108–116.

GB/T 15796—2011. Rules for monitoring and forecast of the wheat head blight (Fusarium graminearum Schw./Gibberella zeae (Schw.) Petch). Standardization Administration of China, 2011. (in Chinese)

Xie A G, Sun D-W, Zhu Z W, Pu H B. Nondestructive measurements of freezing parameters of frozen porcine meat by NIR hyperspectral imaging. Food and Bioprocess Technology, 2016; 9: 1444–1454.

Alisaac E, Behmann J, Kuska M T, Dehne HW, Mahlein A K. Hyperspectral quantification of wheat resistance to Fusarium head blight: Comparison of two Fusarium species. European Journal of Plant Pathology, 2018; 152: 869–884.

Zhang D Y, Xu L, Liang D, Xu C, Jin X L, Weng S Z. Fast prediction of sugar content in Dangshan pear (Pyrus spp.) using hyperspectral imagery data. Food Analytical Methods, 2018; 11: 2336–2345.

Ma J, Cheng J-H, Sun D-W, Liu D. Mapping changes in sarcoplasmatic and myofibrillar proteins in boiled pork using hyperspectral imaging with spectral processing methods. LWT, 2019; 110: 338–345.

Liang K, Zhang X X, Ding J, Xu J H, Han D S, Shen M X. Discrimination of wheat scab infection level by Fourier mid-infrared technology combined with sparse representation based on classified method. Spectroscopy and Spectral Analysis, 2019; 39: 3251–3255. (in Chinese)

Zhu M Y, Yang H B, Li Z W. Early detection and identification of rice sheath blight disease based on hyperspectral image and chlorophyll content. Spectroscopy and Spectral Analysis, 2019; 39(6): 1898–1904. (in Chinese)

Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012; 25(2): 3065386.

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Computer Science, 2014 .

Zeiler M D, Masum R. Visualizing and understanding convolutional networks. In: ECCV 2014, Zürich, Switzerland: Springer Science, Business Media, 2014; pp.818–833.

He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA: IEEE, 2016; pp.770–778.

Wilson D R, Martinez T R. The need for small learning rates on large problems. In: IEEE International Joint Conference on Neural Networks, Washington, DC, USA: IEEE, 2002; pp.115–119.

Abbas Q, Bangyal W H, Ahmad J. Analysis of learning rate using BP algorithm for hand written digit recognition application. In 2010 International Conference on Information and Emerging Technologies, Karachi, Pakistan: IEEE, 2010; pp.1–5.

Smith S L, Kindermans P-J, Le Q V. Don’t decay the learning rate, increase the batch size. ICLR 2018, 2018;

Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. Journal of Machine Learning Research, 2015; 2: 03167.

Gao F F, Fu L S, Zhang X, Majeed Y, Li R, Karkee M, et al. Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN. Computers and Electronics in Agriculture, 2020; 176: 105634.

Peng H X, Huang B, Shao Y Y, Li Z S, Zhang C W, Chen Y, et al. General improved SSD model for picking object recognition of multiple fruits in natural environment. Transactions of the CSAE, 2018; 34(16): 155–162. (in Chinese)




Copyright (c) 2024 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office