Scholarlink

<p>Anthracnose and fruit fly infestation are major biotic constraints on guava (Psidium guajava) production in South Asia, causing substantial yield losses and post-harvest degradation. Early-stage symptoms (lesions &lt; 2&#xa0;mm, subtle puncture marks) are often imperceptible to the naked eye, making timely intervention difficult. This study develops a deep learning-based classification system for early detection of both conditions using a dataset of 473 annotated guava fruit images from Bangladesh, verified by a plant pathologist, and pre-processed with unsharp masking and Contrast Limited Adaptive Histogram Equalization (CLAHE). After data augmentation, four architectures ResNet50, EfficientNetB3, DenseNet121, and Vision Transformer were evaluated using transfer learning with ImageNet pretrained weights. EfficientNetB3 achieved the highest performance: 98.5% accuracy, 98.3% precision, 98.2% recall, and 98.2% F1-score, with minimal cross-class confusion between anthracnose and fruit fly (ROC-AUC = 0.993). Ablation studies confirmed that CLAHE and unsharp masking together improved accuracy by 4.3% over baseline. Computational efficiency analysis showed that EfficientNetB3 (12.3&#xa0;million parameters, 13&#xa0;MB quantized size) achieves 214 ms inference on a Raspberry Pi 4B, confirming edge-deployment feasibility.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning for early detection of guava fruit anthracnose and fruit fly infestation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月28日

查看全文
  • Aniket K. Shahade,
  • Gaikwad Vidya Shrimant,
  • Madhura Phadke,
  • Vidula V. Meshram,
  • Vishal A. Meshram,
  • Disha Sushant Wankhede,
  • Makarand R. Shahade

摘要

Anthracnose and fruit fly infestation are major biotic constraints on guava (Psidium guajava) production in South Asia, causing substantial yield losses and post-harvest degradation. Early-stage symptoms (lesions < 2 mm, subtle puncture marks) are often imperceptible to the naked eye, making timely intervention difficult. This study develops a deep learning-based classification system for early detection of both conditions using a dataset of 473 annotated guava fruit images from Bangladesh, verified by a plant pathologist, and pre-processed with unsharp masking and Contrast Limited Adaptive Histogram Equalization (CLAHE). After data augmentation, four architectures ResNet50, EfficientNetB3, DenseNet121, and Vision Transformer were evaluated using transfer learning with ImageNet pretrained weights. EfficientNetB3 achieved the highest performance: 98.5% accuracy, 98.3% precision, 98.2% recall, and 98.2% F1-score, with minimal cross-class confusion between anthracnose and fruit fly (ROC-AUC = 0.993). Ablation studies confirmed that CLAHE and unsharp masking together improved accuracy by 4.3% over baseline. Computational efficiency analysis showed that EfficientNetB3 (12.3 million parameters, 13 MB quantized size) achieves 214 ms inference on a Raspberry Pi 4B, confirming edge-deployment feasibility.