Abstract
Ensuring food security is a crucial priority for nations worldwide, but plant diseases significantly hinder this objective, through their impacts on agricultural productivity. Chili pepper ( Capsicum spp. ) is a major crop in West Africa including in Benin. However, its production is challenged by diseases such as anthracnose and Tomato Yellow Leaf Curl Virus (TYLCV) which severely impact its yields and farmer livelihoods. While traditional methods for disease detection and management have been commonly used, they are no longer sufficient to combat rising pest infestations and declining agricultural productivity. To tackle this issue, we built a comprehensive dataset of 213 images of anthracnose-affected leaves, 202 images of TYLCV-infected leaves, and 119 images of healthy leaves, collected under diverse environmental conditions in Benin. The study compared the performance of thirteen (13) deep learning models including among others YOLOv8, MobileNetV2, and DenseNet121 for the classification of chili diseases in Benin using transfer learning techniques to improve their accuracy, based on values close to one (1) of evaluation metrics such as Accuracy, Precision, Recall and F1-Score. Results show that YOLOv8 outperforms other models in detecting and localizing leaf diseases in real time. It achieved a mean Average Precision (mAP@0.5) of 0.995 and mAP@0.5–0.95 of 0.941, demonstrating strong generalization. With precision and recall exceeding 99%, YOLOv8 proves highly reliable for agricultural applications. Among classification models, MobileNetV2 and DenseNet121 achieved 96.25% accuracy, confirming their effectiveness in disease classification. Our findings demonstrate that deep learning models, particularly YOLOv8, hold immense potential for real-time, automated detection of chili pepper diseases. Future research should focus on expanding datasets, integrating climatic variations, and improving disease severity assessment for enhanced agricultural sustainability.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 5
Claim · model-written summary
YOLOv8 outperformed other models in detecting and localizing chili pepper leaf diseases in real time.
- Treatment
- YOLOv8e1
- Outcome
- detecting and localizing leaf diseasese1
- Direction
- outperformse1
- Comparator
- other modelse1
CapsicumOrganisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“chili pepper disease detection”
e1“Results show that YOLOv8 outperforms other models in detecting and localizing leaf diseases in real time”
Claim · model-written summary
YOLOv8 achieved a mean Average Precision (mAP@0.5) of 0.995 for chili pepper disease detection.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“chili pepper disease detection”
e2“It achieved a mean Average Precision (mAP@0.5) of 0.995 and mAP@0.5–0.95 of 0.941”
Claim · model-written summary
YOLOv8 achieved a mAP@0.5–0.95 of 0.941 for chili pepper disease detection.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“chili pepper disease detection”
e2“It achieved a mean Average Precision (mAP@0.5) of 0.995 and mAP@0.5–0.95 of 0.941”
Claim · model-written summary
YOLOv8 precision and recall exceeded 99%.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“chili pepper disease detection”
e3“With precision and recall exceeding 99%”
Claim · model-written summary
MobileNetV2 and DenseNet121 achieved 96.25% accuracy in chili pepper disease classification.
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“chili pepper disease detection”
e4“MobileNetV2 and DenseNet121 achieved 96.25% accuracy”