Abstract:
Kiwi leaf disease manual detection is a time-consuming method that typically calls for the understanding of actual professionals. This study presents a machine learning a...Show MoreMetadata
Abstract:
Kiwi leaf disease manual detection is a time-consuming method that typically calls for the understanding of actual professionals. This study presents a machine learning approach for the automated detection of kiwi leaf diseases. The proposed method makes use of a dataset of annotated photos to differentiate healthy and sick kiwi leaves. The proposed approach has the potential to greatly reduce the amount of time and money required for kiwi leaf disease detection, enabling more rapid and efficient management of kiwi agricultural production. In this study, the kiwi fruit leaf illnesses were detected using a machine learning CNN & SVM approach. This is one of the key research areas in education. The proportion used to split the information into training and validation was 80:20 during the execution of this research. Our experimental results demonstrate that, with an overall accuracy of 83.34%, the proposed approach successfully detected 5 different forms of kiwi leaf diseases, namely Healthy leaf, Anthracnose, Brown spot, Bacterial canker, and Mosaic. The suggested method can be used for other types of plant disease detection as well, and it can significantly reduce the time and money associated with the manual detection of kiwi leaf diseases.
Published in: 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)
Date of Conference: 14-16 March 2023
Date Added to IEEE Xplore: 20 April 2023
ISBN Information: