DATA COLLECTION TECHNIQUES FOR LEAF DISEASE DETECTION: A SYSTEMATIC REVIEW

Abstract

For ensuring crop health and agricultural productivity accurate and timely detection of leaf diseases is important. Due to advancement in sensor technologies and imaging modalities, various data collection techniques have emerged to support automated disease detection. This systematic review aims to distinguish and explain various kinds of data gathered for leaf disease detection (e.g., visual, multispectral, hyperspectral, thermal). Different methods of data acquisition are analyzed such as field-based sensing, remote sensing and laboratory analysis. The advantages and disadvantages of each data collection technique should be identified. The insights and recommendations are provided to researchers and practitioners in the selection of appropriate data collection strategies. explore and categorize the various types of data used in leaf disease detection, including visual, multispectral, hyperspectral, and thermal imaging data. It further analyzes different methods of data acquisition, such as field-based sensing, remote sensing via aerial or satellite platforms, and controlled laboratory analysis. Each technique is evaluated in terms of its precision, scalability, cost-effectiveness, and applicability across different crop types. The review highlights the strengths and limitations inherent to each data collection approach and provides practical insights to guide researchers and practitioners in selecting suitable strategies tailored to specific diagnostic goals and resource constraints. Through this synthesis, the paper contributes to the development of more effective and context-aware plant disease monitoring systems.