Enhancing Cauliflower Yield through Automated Leaf Disease Classification

This paper proposes a type approach that is famous for incredible performance metrics and is supposed to appropriately identify distinct types of cauliflower leaf illnesses. With Bacterial Soft Rot acquiring the highest precision of 96.53%, the precision prices display high accuracy and demonstrate the model’s capacity to appropriately diagnose infected occurrences. Recall fees provide additional evidence of the version’s efficacy, specifically with regards to Fusarium Wilt and Clubroot, which both have recollect rankings of ninety 65% and 96.45%, respectively, demonstrating wonderful detection capabilities. With 11,150 photos used to educate it, the model’s total accuracy changed to 96.32%. All disease classes showcase comparable type performance, as evidenced by the F1-ratings, which balance consideration and precision and vary from 96.12% for Downy Mildew to 96.53% for Bacterial Soft Rot. With the best aid of 1440 instances for Bacterial Soft Rot, the aid values display a properly dispensed dataset, ensuring accurate model schooling and evaluation. With an amazing 99% accuracy price in all classes, the version is particularly noteworthy and shows promise for actual international use in agricultural settings for early disease analysis. As a result, the model is placed as a useful device for farmers seeking to reduce the effects of cauliflower leaf illnesses. Its effectiveness additionally allows desirable crop management and raises normal agricultural output.