ABSTRACT
The detection of pesticide residue in vegetables is becoming evident in modernized agriculture. Our present work used visible/near-infrared (400–1000 nm) Hyperspectral Imaging Systems (HSIs) to detect the pesticide residue levels in Brinjal. This paper proposes a deep learning framework named the 3D Squeeze Excitation-Residual Spectral Network (3D SERSN) that takes raw 3-D cubes as input data without feature engineering for hyperspectral image classification. In this network, the spectral residual blocks consecutively learn discriminative features from abundant spectral signatures and the newly introduced SE block inside the residual block keeps the skip connection branch as clean as possible to make the learning identity easy. The proposed network is evaluated on the developed HSI dataset of Brinjals. Image samples were captured using a hyperspectral camera for Brinjals without pesticide and with pesticides at different concentrations of 0.5ml, 3ml and 6ml in 1 litre of water namely low, medium and high. Two types of classification analysis, two classes (with or without pesticide) and four classes (pure, low, medium and high) were done with a set of machine learning algorithms and using the proposed deep network. The classification analysis was also implemented with seven machine learning algorithms and with a CNN. For the four-class classification problem, the Multi-class support vector machine and the Discriminant analysis Algorithm reported the highest accuracy of 89%; for the two-class classification, the K-nearest neighbour classifier recorded the highest accuracy of 78%. The proposed 3D SERSN gives an accuracy of 94% for the two-class problem and 98% for the four-class problem on the proposed dataset for pesticide residue estimation on brinjals, showing the effectiveness of our suggested network for the stated issue.1
- Usha Z Dattatray S, Meena Patil and Srinivas Parimi. 2012. Evaluation of newer insecticides for the management of brinjal fruit and shoot borer Leucinodes orbonalis. Indian Journal of Plant Protection Vol 40, No 4, 2012 (273-275) (2012).Google Scholar
- P. Grimalt, S.; Dehouck. 2016. Review of analytical methods for the determination, of pesticide residues in grapes. A Incl. Electrophor. Other Sep. Methods 2016, 1433, 1–23 (2016).Google Scholar
- J.R.; Fu H.F.; Shao X.T.; Li Z.K Jia, Y.G.; He. 2018. Apple Surface Pesticide Residue Detection Method Based on Hyperspectral Imaging.Intell. Sci. Big Data Eng. 2018, 11266, 539–556 (2018).Google Scholar
- J.; Xin Z.; Mao H.; Wu X.; Li Q. Jiang, S.; Sun. 2017. Visualizing distribution of pesticide residues in mulberry leaves using NIR hyperspectral imaging. J. Food Process Eng. 2017, 40, e12510.1–e12510.6 (2017).Google Scholar
- J.; Yang S.; Fu H.; Li T.; Song H Jiang, B.; He. 2019. Fusion of machine vision technology and Alexnet-CNNs deep learning network for the detection of postharvest apple pesticide residues.Artificial Intelligence. Agric. 2019, 1, 1–8. (2019).Google Scholar
- W.; Fang L.; Chen Y.; Benediktsson J.A. Li, S.; Song. 2019. Deep learning for hyperspectral image classification: An overview.IEEE Trans. Geosci. Remote Sens. 2019, 57, 6690–6709. (2019).Google Scholar
- Jiangtao Peng Li Wang and Weiwei Sun. 2019. Spatial–Spectral Squeeze-and-Excitation Residual Network for Hyperspectral Image Classification. Remote Sens. MDPI, 2019, 11, 884; doi:10.3390/rs11070884 (2019).Google ScholarCross Ref
- Y.; Pappula S.; Shabeer T.P.A.; Sawant S.D.; Hingmire S Mohite, J.; Karale. 2017. Detection of pesticide (Cyantraniliprole) residue on grapes using hyperspectral sensing. In Sensing for Agriculture and Food Quality and Safety IX; SPIE: Bellingham,WA, USA, 2017 (2017).Google Scholar
- J.M.; Plaza J.; Plaza A. Paoletti, M.E.; Haut. 2019. Deep learning classifiers for hyperspectral imaging: A review.ISPRS J. Photogramm. Remote Sens. 2019, 158, 279–317. (2019).Google Scholar
- J.M.; Plaza J.; Plaza A. Paoletti, M.E.; Haut. 2019. Deep learning classifiers for hyperspectral imaging: A review.ISPRS J. Photogramm. Remote Sens. 2019, 158, 279–317. (2019).Google Scholar
- P.M.; Mena-Morales A.; Martinez-Gascuena Perez-Navarro, J.; Izquierdo-Canas. 2019. Phenolic compounds profile of different berry parts from novel Vitis vinifera L. red grape genotypes and Tempranillo using HPLC-DAD-ESI-MS/MS: A varietal differentiation tool. A varietal differentiation tool. Food Chem. 2019, 295, 350–360 (2019).Google Scholar
- Z.H.; Ji H.Y. Ren, Z.Q.; Rao. 2018. Identification of Different Concentrations Pesticide Residues of Dimethoate on Spinach Leaves by Hyperspectral Image Technology.Ifac Pap. Online 2018, 51, 758–763(2018).Google Scholar
- Liu C Guo L Chen WH. Su J, Yi D. 2017. Dimension Reduction Aided Hyperspectral Image Classification with a Small-sized Training Dataset: Experimental Comparisons.Sensors (Basel). 2017 Nov 25;17(12):2726. doi: 10.3390/s17122726. PMID: 29186846; PMCID: PMC5750527(2017).Google ScholarCross Ref
- S.L.; Mao H.P.; Wu X.H.; Yang N Sun, J.; Cong. 2018. Quantitative detection of mixed pesticide residue of lettuce leaves based on hyperspectral technique.J. Food Process Eng. 2018, 41, e12654(2018).Google Scholar
- Long Duan Wei Chen Hao Song-Yifan Zhang Wei Xu Tianying Yan, Chu Zhang and Pan Gao. 2022. Detection of Pesticide Residue Level in Grape Using Hyperspectral Imaging with Machine Learning,. Foods 2022, 11, 1609(2022).Google Scholar
Index Terms
- Pesticide Residue Estimation in Brinjals using 3D Squeeze Excitation-Residual Spectral Network (SERSN) ✱
Recommendations
Deep Residual Attention Network for Spectral Image Super-Resolution
Computer Vision – ECCV 2018 WorkshopsAbstractSpectral imaging sensors often suffer from low spatial resolution, as there exists an essential tradeoff between the spectral and spatial resolutions that can be simultaneously achieved, especially when the temporal resolution needs to be ...
Spatial-Spectral Deep Residual Network for Hyperspectral Image Super-Resolution
AbstractRecently, single hyperspectral image super-resolution (SR) methods based on deep learning have been extensively studied. However, there has been limited technical development focusing on single hyperspectral image super-resolution due to the high-...
3D residual spatial–spectral convolution network for hyperspectral remote sensing image classification
AbstractHyperspectral remote sensing images (HRSI) are 3D image cubes that contain hundreds of spectral bands and have two spatial dimensions and one spectral dimension. HRSI analysis are commonly used in a wide variety of applications such as object ...
Comments