Abstract
The quality and quantity of agricultural products are significantly affected by plant diseases. The plant diseases could be mitigated if identified at an early stage. In general, the assessment of plant diseases is performed by human raters. There are some disadvantages in recognizing the plant disease in the leaves when observed by human raters. In this research work, an alternate machine learning based feature extraction technique named fractional weighted nuclear norm based two-dimensional linear discriminant analysis (FNN-2DLDA) is proposed to identify the cucumber leaf diseases. The proposed machine learning approach mainly comprises of three phases: firstly, the nuclear norm reveals the spatial relationship between pixels in each leaf image. Secondly, the fractional weight is assigned to weaken the effect of edge class problem (when a greater number of disease classes are present). Finally, the multi-class hierarchical support vector machine (HSVM) classifier is implemented to recognize the cucumber leaf diseases. The proposed machine learning based system contribute to protection and enhancement of leaf species thus resulting in environmental and Gross Domestic Product (GDP) improvement of the nation. The performance metrics, viz. similarity index, recognition rate, confusion matrix based statistical measurements and hypothesis test results of the proposed technique are compared with the existing start-of-the-art techniques. The disease recognition accuracy of the proposed techniques is 87.5%, 88%, 85% and also 95% of confidence in statistical hypothesis testing of unilateral and bilateral procedures. The results show that the proposed FNN-2DLDA technique outperforms the existing techniques which is attributed to the incorporation of nuclear norm and fractional weight into conventional 2DLDA.
Similar content being viewed by others
References
Aakif A, Khan MF (2015) Automatic classification of plants based on their leaves. Biosystems Engineering 139:66–75
Al-Bashish D, Braik M, Bani-Ahmad S (2011) Detection and classification of leaf diseases using K-means-based segmentation and neural networks based classification. Inform Technol J, 267–275. https://doi.org/10.3923/itj.2011.267.275
Arivazhagan S, NewlinShebiah R, Ananthi S, Vishnu Varthini S (2013) Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features. Agric. Eng. Int. CIGR J 15(1):211–217
Bai X, Li X, Zetian F, Lv X, Zhang L (2017) A fuzzy clustering segmentation method based on neighborhood grayscale information for defining cucumber leaf spot disease images. Comput Electron Agric 136(2017):157–165. https://doi.org/10.1016/j.compag.2017.03.004
Chaki J, Parekh R, Bhattacharya S (2015) Plant leaf recognition using texture and shape features with neural classifiers. Pattern Recogn Lett 58:61–68
Chouhan SS, Kaul A, Singh UP, Jain S (2018) Bacterial foraging optimization based radial basis function neural network for identification and classification of plant leaf diseases: an automatic approach towards plant pathology. IEEE Access 6(2018):8852–8864. https://doi.org/10.1109/ACCESS.2018.2800685
El Sghair M, Jovanovic R, Tuba M (2017) An algorithm for plant diseases detection based on color features. Int J Agricult Sci 2:1–6
Gavhale KR, Ujwalla G (2014) An overview of the research on crop leaves disease detection using image processing techniques. IOSR J Comput Eng (IOSR-JCE) 16(1):10–16
Gayathri Devi T, Neelamegam P, Srinivasan A (2018) Plant leaf disease detection using K means segmentation. Int J Pure Appl Math 119(15):3477–3483
Gurubelli Y, Ramanathan M, Ponnusamy P (2019) Fractional fuzzy 2DLDA approach for pomegranate fruit grade classification, computers and electronics in agriculture Volume 162:95–105. https://doi.org/10.1016/j.compag.2019.03.036
Gutte VS, Gitte MA (2016) A survey on recognition of plant disease with help of algorithm. Int J Eng Sci 7100
Kanjalkar HP, Lokhande SS (2014) Feature extraction of leaf diseases. International Journal of Advanced Research in Computer Engineering & Technology 3(1):153–155
Kaur S, Pandey S, Goel S (2018) Semi-automatic leaf disease detection and classification system for soybean culture. IET Image Process 12(6):1038–1048
Kheirkhah FM, Asghari H (2019) Plant leaf classification using GIST texture features. IET Comput Vis 13(4):369–375
Lee SH, Chan CS, Mayo SJ, Remagnino P (2017) How deep learning extracts and learns leaf features for plant classification. Pattern Recognition 71:1–13
Li X, Hu W, Wang H, Zhang Z (2010) Linear discriminant analysis using rotational invariant L1 norm. Neurocomputing 73:2571–2579. https://doi.org/10.1016/j.neucom.2010.05.016
Lu Y, Yuan C, Lai Z, Li X, Zhang D, Wong WK (2018) Horizontal and vertical nuclear norm-based 2DLDA for image representation. IEEE Trans Circuits Syst Video Technol, 1051–8215 (c), 1–14. https://doi.org/10.1109/TCSVT.2018.2822761
Ma J, Keming D, Zheng F, Zhang L, Gong Z, Sun Z (2018) A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network. Comput Electron Agric 154(2018):18–24. https://doi.org/10.1016/j.compag.2018.08.048
Mohanty SP, Hughes DP, Salathé M (2016) Using deep learning for image-based plant disease detection. Front Plant Sci 7. https://doi.org/10.3389/fpls.2016.01419. Article: 1419.
Padmavathi K, Thangadurai K (2016) Implementation of RGB and grayscale images in plant leaves disease detection – comparative study. Indian J Sci Technol 9(6):1–6. https://doi.org/10.17485/ijst/2016/v9i6/77739
Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of crop diseases with support vector machines based on hyperspectral reflectance. Comput Electron Agric 74(1):91–99
Tharwat A, Gaber T, Ibrahim A, Ibrahim A (2017) Linear discriminant analysis: a detailed tutorial. AI Commun 30:169–190. https://doi.org/10.3233/AIC-170729IOSPress
Valliammal N, Geethalakshmi SN (2012) Plant leaf segmentation using non linear K means clustering. Int J Comput Sci 9, Issue 3, 1, 212–218.
Wang H, Lu X, Hu Z, Zheng W (2014) Fisher discriminant analysis with L1-norm. IEEE Trans Cybern 44(6):828–842. https://doi.org/10.1109/tcyb.2013.2273355
Xu G (2019) Chen Li and qi Wang, unified multi-scale method for fast leaf classification and retrieval using geometric information. IET Image Process 13(12):2328–2334
Yang, Xin, Guo T (2017) Machine learning in plant disease research. Europ J BioMed Res. 6–9. https://doi.org/10.18088/ejbmr.3.1.2016.pp6-9.
Yang W, Yan X, Zhang L, Sun C (2010) Feature extraction based on fuzzy 2DLDA. Neurocomputing 73(10–12):1556–1561. https://doi.org/10.1016/j.neucom.2009.12.025
Zhang SW, Shang YJ, Wang L (2015) Plant disease recognition based on plant leaf image. J Animal Plant Sci 25(3):42–45
Zhang F, Yang J, Qian J, Xu Y (2015) Nuclear norm-based 2-DPCA for extracting features from images. IEEE Trans Neural Netw Learn Syst 26(10):2247–2260. https://doi.org/10.1109/TNNLS.2014.2376530
Zhang S, Wu X, You Z, Zhang L (2017) Leaf image based cucumber disease recognition using sparse representation classification. Comput Electron Agric 134:135–141. https://doi.org/10.1016/j.compag.2017.01.014
Zhang S, Zhang S, Zhang C, Wang X, Shia Y (2019) Cucumber leaf disease identification with global pooling dilated convolutional neural network. Comput Electron Agric 162(2019):422–430. https://doi.org/10.1016/j.compag.2019.03.012
Zhang P, Deng S, Nie F, Yang L, Zhang XD, Gao QX (2019) Nuclear-norm based 2DLDA with application to face recognition. Neurocomputing 339(2019):94–104. https://doi.org/10.1016/j.neucom.2019.01.066
Zhao C, Chan SSF, Cham W-K, Chu LM (2015) Plant identification using leaf shapes-A pattern counting approach. Pattern Recognition 48:3203–3215
Zhong F, Zhang J (2013) Linear discriminant analysis based on L1-norm maximization. IEEE Trans Image Process 22(8):3018–3027. https://doi.org/10.1109/TIP.2013.2253476
Acknowledgements
The authors would like to thank Dr. Shanwen Zhang, Department of Electronics and Information Engineering, XiJing University, Xi’an 710123, China for providing the access to use the cucumber leaf image database. Sincere thanks to Dr. S Domnic, Artificial Intelligence, Center of Excellence, Department of Computer Applications, National Institute of Technology Trichy, India for providing access to use the GPU workstation for simulations.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yogeswararao, G., Malmathanraj, R. & Palanisamy, P. Fractional weighted nuclear norm based two dimensional linear discriminant features for cucumber leaf disease recognition. Multimed Tools Appl 81, 38735–38755 (2022). https://doi.org/10.1007/s11042-022-13013-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13013-9