A comprehensive Malabar Spinach dataset for diseases classification

Abstract

This study focuses on the urgent need to increase detection of diseases in Malabar Spinach, a valuable leaf vegetable crop which is at risk from several disease types including Anthracous leaf spot and Straw mite infestation. There is still a lack of research focused on Malabar spinach, although advances in machine vision have considerably increased the detection of largescale crop diseases. By developing and evaluating machine vision algorithms specifically designed for accurate detection of diseases in Malabar spinach, this research aims to fill this gap. To achieve this, a comprehensive dataset comprising images of both healthy and diseased Malabar Spinach plants is utilized for training, testing, and validation purposes. This study seeks to develop reliable disease detection models through the examination of different image processing techniques and deep learning algorithms such as ResNet50. In particular, the performance of these models is rigorously evaluated on the basis of a set of standardized evaluation metrics which aim to achieve an overall test accuracy of 94%. The results of this research will have a major impact on the cultivation of Malabar spinach in terms of precision farming techniques and effective crop management practices. This study will contribute to the wider objectives of agricultural sustainability and food security, through increasing crop productivity and reducing yield losses. In the end, it is intended to strengthen the resilience of farming communities dependent on Malabar Spinach crops by providing farmers and experts with efficient tools for detecting diseases.