Comparative Study on Cassava Leaf Disease Classification

Abstract

Manihot esculenta, the scientific name for cassava, is an important staple crop that feeds millions of people in tropical countries and provides a substantial amount of carbohydrates. To minimize these losses and guarantee food security, it is essential to identify plant illnesses as early as possible. Using innovative technology in image processing and machine learning, this comparative study explores the field of classifying illnesses of cassava leaves. The need for efficient and mechanized disease detection methods is pressing, and it might have a significant impact on food security and agricultural sustainability. our is the driving force behind our research. Code examples for processing data and machine learning model implementation are included in the research, together with the compilation and labelling of an extensive dataset. The findings and outcomes from the tests on disease classification are carefully explained. Accompanying them is a comprehensive examination of the assessment metrics, encompassing ROC curves, cross-validation outcomes, recall, accuracy, and a F1 score. These results not only highlight the effectiveness of the suggested methodology but also provide a comparative evaluation of various models and techniques. The study's comparison assessment and investigation findings highlight the possibility for more precise and scalable illness detection methods, providing a foundation for further research in this area.

Topics & Concepts