CNN-SVM Model for Accurate Detection of Bacterial Diseases in Cucumber Leaves

This research paper presents a deep learning approach for detecting and classifying plant diseases in citrus crops. The proposed model uses a convolutional neural network (CNN) architecture with three convolutional layers, three pooling layers, and two fully connected layers, followed by support vec...

Full description

Saved in:
Bibliographic Details
Published in2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC) pp. 7 - 12
Main Authors Banerjee, Deepak, Kukreja, Vinay, Hariharan, Shanmugasundaram, Jain, Vishal, Dutta, Soumi
Format Conference Proceeding
LanguageEnglish
Published IEEE 26.05.2023
Subjects
Class
Computational modeling
Crops
Diseases
Industries
Microorganisms
Plant diseases
precision
Predictive models
Support vector machines
Online AccessGet full text
DOI10.1109/ICSCCC58608.2023.10176783

Cover

More Information
Summary:This research paper presents a deep learning approach for detecting and classifying plant diseases in citrus crops. The proposed model uses a convolutional neural network (CNN) architecture with three convolutional layers, three pooling layers, and two fully connected layers, followed by support vector machine (SVM) classifiers. The model was trained and tested using a dataset of citrus crop images containing nine different classes of diseases. The performance of the model was evaluated based on precision, recall, F1-score, support, accuracy, and average metrics. The overall accuracy of the model was found to be 86.03%, with a weighted average F1 score of 86.10%. The model achieved the highest precision score of 86.96% for the Citrus nematode class and the lowest precision score of 84.00% for the Dothiorella blight class.
DOI:10.1109/ICSCCC58608.2023.10176783