International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023
p-ISSN: 2395-0072
www.irjet.net
POMDETECT: AN INVESTIGATION INTO LEAF DISEASE DETECTION TECHNIQUES Prof. Prashant Wakhare1, Rutvija Patil2, Jayash Kandalkar3, Sonali Kalme4, Rushikesh Kawtikwar5 Dept. of Information Technology AISSMS’s Institute of Information Technology Pune-1, Maharashtra, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The cultivation of pomegranate has gained
significant attention in recent years due to its numerous health benefits. However, pomegranate plants are highly susceptible to various diseases that affect their productivity and quality. Early detection and diagnosis of these diseases are crucial to prevent their spread and minimize crop losses. In this study, we explore various techniques for pomegranate leaf disease detection, including visual inspection, spectral imaging, and machine learning-based approaches. The effectiveness of each technique in detecting common pomegranate leaf diseases, such as bacterial blight, anthracnose, and powdery mildew, using a dataset of highresolution leaf images. Our study shows that machine learning-based approaches, particularly convolutional neural networks (CNNs), outperform other techniques in terms of accuracy and speed. This study provides insights into the current state of pomegranate leaf disease detection techniques and highlights the need for further research to develop more accurate and efficient detection methods.
Figure [1] Pomegranate leaf diseases detection techniques for Bacterial Blight The image depicted in Figure [1] provides details about the different methods employed to detect Pomegranate leaf diseases, with a particular emphasis on assessing bacterial blight. This type of disease is a frequent occurrence that can significantly harm pomegranate crops by damaging the leaves. To detect this disease, several techniques can be used, including:
Keywords- Visual Inspection, Spectral Imaging, Machine Learning, Convolutional Neural Networks (CNNs), Accuracy, Speed, Automated disease monitoring, Effective management.
1. INTRODUCTION
Phenotype assessment: This method involves observing the physical symptoms of the disease on the leaves, such as yellowing, wilting, and necrosis.
To investigate various techniques for pomegranate leaf disease detection, including visual inspection, spectral imaging, and machine learning-based approaches. The effectiveness of each technique in detecting common pomegranate leaf diseases using a dataset of highresolution leaf images. Our study provides insights into the current state of pomegranate leaf disease detection techniques and highlights the potential of integrating these techniques into automated disease monitoring systems. This study aims to contribute to the development of more accurate and efficient methods for pomegranate leaf disease detection and management.
© 2023, IRJET
|
Impact Factor value: 8.226
PCR (Polymerase Chain Reaction): This technique involves amplifying the DNA of the pathogen causing the disease and detecting it using specific primers. PCR can be further divided into two categories: Age PCR (Agarose gel electrophoresis PCR): This method involves visualizing the amplified DNA using agarose gel electrophoresis. CE (Capillary Electrophoresis): This technique involves separating and detecting the amplified DNA using capillary electrophoresis.
|
ISO 9001:2008 Certified Journal
|
Page 1848