REGULARIZED ISOTONIC REGRESSION BASED JENSEN-SHANNON BOOSTING CLASSIFICATION FOR PLANT LEAF DISEASE IDENTIFICATION
Keywords:
Plant leaf disease identification, preprocessing, segmentation, feature extraction classificationAbstract
Automatic plant leaf disease identification and classification systems are important for precision agriculture. Fast and accurate identification of leaf diseases is a vital problem solved in agriculture and prevents losses. To enhance the accuracy of plant leaf disease identification, Regularized Perona-Malik Segmentive Isotonic Regression-based Jaccard Jensen-Shannon Boosting Classification (RPMSIR-JJSBC) technique is introduced. The proposed technique includes five processing steps. Initially, the image acquisition process is performed to collect multiple rice plant leaf images with IoT. Secondly, input rice plant leaf images are preprocessed to improve quality by removing noises. Thirdly, region-based segmentation is performed to partition images into number of segments. Next, weighted Isotonic Regression is applied to minimize disease identification time. Finally, extracted features are analyzed and classify the image into normal or disease with higher accuracy. Thus, RPMSIR-JJSBC technique performs disease identification. The simulation result demonstrates different parameters namely peak signal to noise ratio, disease identification accuracy, false-positive rate, and disease identification time.
References
Aakrati, N., Avdhesh, K.T., and Akhilesh P. (2020). Paddy leaf diseases recognition and classification using PCA and BFODNN algorithm by image processing. In: International Conference on Nanotechnology: Ideas, Innovation, and Industries, Netherlands (NLD), Materials Today: Proceedings, p. 4,856-4,862.
Bin, L., Cheng, T., Shuqin L., Jinrong H., and Hongyan W. (2020). A data augmentation method based on generative adversarial networks for grapse leaf disease identification. IEEE Access, 8:102,188-102,198.
Chen, J., Yin H., and Zhang, D. (2020). A self-adaptive classification method for plant disease detection using GMDH-Logistic model. Sustain. Comp. Inform. Sys., 28:100,415
David, F.N., Dimitrios K., Argyris K., Natasa S., Pau. P., and Roberto, C. (2019). Predicting rice blast disease: machine learning versus process-based models. BMC Bioinform., 20: 1-16.
Deepak, G., Prerna, S., Krishna, C., Kshitij, G., Rahul, C., Ashish, K., Victor H.C. d. A. (2020). Artificial plant optimization algorithm to detect infected leaves using machine learning Expert Systems, (Special Issue Paper): e12490.
Guoxiong, Z., Wenzhuo, Z., Aibin, C.,Mingfang, H., and Xueshuo, M. (2019). Rapid detection of rice disease based on FCM-KM and faster R-CNN fusion. IEEE Access., 7:143,190-143,206.
Jie, H., Dexiang, Z., Peng, C., Jun, Z., and Bing, W. (2019). Classification of plant leaf diseases based on improved convolutional neural network. Sensors, 19(19):4,161.
Junde, C., Defu Z., Md, S., Yaser, A.N., and Yuandong, S. (2020a). Identification of plant disease images via a squeeze-and-excitation MobileNet model and twice transfer learning. IET Image Processing, 15(5):1,115-1,127.
Junde, C., Defu, Z., Yaser, A.N., and Dele, L. (2020b). Detection of rice plant diseases based on deep transfer learning, J. Sci. Food Agri., 100(7):3,246-3,256.
Lohith, K.P., Vinay K.K.G., Vasanth K.G., and Shijin K.P.S. (2020). Enhanced weighted sum back propagation neural network for leaf disease classification. In: Materials Today: Proceedings, p. 1-8.
Mingjie, L., Guoxiong, Z., Mingfang, H., Aibin, C., Wenzhuo, Z., and Yahui, H. (2020), Maize Leaf disease identification based on feature enhancement and DMS-robust alexnet. IEEE Access, 8:57,952-57,966.
Monalisa, M., Prasenjit, C., and Bibudhendu P. (2021). Modified ride NN optimizer for IoT-based plant disease detection. J. Ambi. Intellig. Human. Comp., 12(6):691-703.
Qiang, D., Xi, C., Yan, Q., and Youhua, Z. (2020). Crop leaf disease image superresolution and identification with dual attention and topology fusion generative adversarial network. IEEE Access, 8:55.724-55.735.
Rahman, C.R., Arko, P.S., Ali, M.E., Khan, M.A.I., Apon, S.H., Nowrin, F., and Wasif, A. (2020). Identification and recognition of rice diseases and pests using convolutional neural networks. Biosys. Eng., 194:112-120.
Sachin, B.J. Vishwanath R.U., and Sanjay B.P. (2020). Identification of plant diseases using convolutional neural networks. Int. J. Inform. Technol., p. 1-10.
Sanjeevi, P., Ashwin, M., Manikandan, R., Karthick, R.K.M., and Anantha, R.G.R. (2020). Heterogeneous internet of things organization predictive analysis platform for apple leaf diseases recognition. Comp. Commun., 154:99-110.
Tan, N.P., Ly, V.T., and Son, V.T.D. (2020). Early disease classification of mango leaves using feed-forward neural network and hybrid metaheuristic feature selection. IEEE Access, 8:189,960-189,973.
Toran, V. and Sipi D. (2019). Fuzzy-filtered neural network for rice disease diagnosis using image analysis. Int. J. Inno. Technol. Explo. Eng. (IJITEE)., 8(8S3):437-446.
Vikas, S., Aftab, A.M., and Dr. Abid, S. (2020). Detection of rice disease using bayes’ classifier and minimum distance classifier. J. Multimed. Inform. Sys., 7(1):17-24.
Xiao, C., Guoxiong Z., Aibin, C., Jizheng, Y., Wenzhuo, Z., Yahui, H. (2020). Identification of tomato leaf diseases based on the combination of ABCK-BWTR and B-ARNet. Comp. Elect. Agri., 178:105,730.
