Hybrid Convolutional Neural Network for Plant Diseases Prediction

作     者：S.Poornima N.Sripriya Adel Fahad Alrasheedi S.S.Askar Mohamed Abouhawwash 

作者机构：Department of Information TechnologySri Sivasubramaniya Nadar College of EngineeringChennai603110India Department of Statistics and Operations ResearchCollege of ScienceKing Saud UniversityRiyadh11451Saudi Arabia Department of MathematicsFaculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational MathematicsScienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA 

出 版 物：《Intelligent Automation & Soft Computing》 (智能自动化与软计算（英文）)

年 卷 期：2023年第36卷第5期

页      面：2393-2409页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Supporting Project Number(RSP-2021/323) King Saud University Riyadh Saudi Arabia 

主　　题：Disease detection people detection image classification deep learning region based convolutional neural network 

摘      要：Plant diseases prediction is the essential technique to prevent the yield loss and gain high production of agricultural *** monitoring of plant health continuously and detecting the diseases is a significant for sustainable *** system to monitor the diseases in plant is time consuming and report a lot of *** is high demand for technology to detect the plant dis-eases *** image processing approach and deep learning approach are highly invited in detection of plant *** diseases like late blight,bacterial spots,spots on Septoria leaf and yellow leaf curved are widely found in *** are the main reasons to affects the plants life and *** identify the diseases earliest,our research presents the hybrid method by com-bining the region based convolutional neural network(RCNN)and region based fully convolutional networks(RFCN)for classifying the *** the leaf images of plants are collected and preprocessed to remove noisy data in *** data normalization,augmentation and removal of background noises are *** images are divided as testing and training,training images are fed as input to deep learning ***,we identify the region of interest(RoI)by using selective *** every region,feature of convolutional neural network(CNN)is extracted independently for further classifi*** plants such as tomato,potato and bell pepper are taken for this *** plant input image is analyzed and classify as healthy plant or unhealthy *** the image is detected as unhealthy,then type of diseases the plant is affected will be *** proposed technique achieves 98.5%of accuracy in predicting the plant diseases.