Grapevine leaves Image classification

Keywords: Grapevine, leaves

Background

Grapevine leaves classification is an important task in agriculture, aiming to differentiate between healthy and diseased leaves for early detection of plant diseases. Deep learning techniques, particularly Convolutional Neural Networks (CNN), have shown significant success in image classification tasks. However, classifying grapevine leaves presents specific challenges, such as variations in leaf size and shape, as well as the need for normalizing multiple batches and increasing epochs for effective learning from the dataset. The images must be preprocessed by resizing them to the same pixel sizes. In this study, the author applied a CNN model with multiple max pooling layers to classify grapevine leaves. After a comprehensive analysis of different leaf images, the CNN model achieved an accuracy score of 35%. This outcome demonstrates the potential of CNN-based approaches for accurate grapevine leaf classification, aiding in the early detection and management of diseases in vineyards. Overall, the Grapevine leaves classification will help in leading to improved crop production.

Aim & Objectives

Aim
To Classify a image of Grapevine leaves Using DL techniques
Objective

Implement an ANN model to accurately classify grapevine leaves, aiding in disease detection and vineyard management.
Develop an ANN system that analyzes leaf images to identify different types of diseases or stress factors.
Evaluate the ANN's classification performance, contributing to improved grapevine health monitoring and crop yield.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —