Scholarlink

<p>Accurate and rapid identification of quarantine-significant tephritids is critical to global agricultural biosecurity, but the application of deep learning is limited by the lack of large public image datasets. We present Tephritid26, a multi-angle image dataset of 26 tephritid species to address this gap. The dataset includes 38,081 images from 1,473 specimens across seven genera and two subfamilies, assembled through a global collaborative effort to source these regulated species. Specimens were mounted using a novel protocol combining varied thoracic attachment points and pin angles, and a rotational imaging setup then systematically captured each specimen from multiple perspectives to mimic real inspection conditions. The dataset is formatted for machine learning workflows. To demonstrate its utility, we trained deep learning models for species identification. ResNet-50, ConvNeXt-B, Vit-Small and Swin-Tiny all attained high species-level accuracy (Macro-Averaged F1-score &gt; 96.75). Gradient-weighted Class Activation Mapping confirmed that the models focused on taxonomically informative morphological regions. This dataset serves as a benchmark for developing automated identification tools in phytosanitary applications.</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

Tephritid26: A standardized, multi-angle image dataset of quarantine-significant true fruit flies for deep learning-based identification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月27日

查看全文
  • Zitao Li,
  • Xingkai Wang,
  • Zhuojie Wu,
  • Mengyuan Yong,
  • Marc De Meyer,
  • Kostas Bourtzis,
  • Bingbing Wei,
  • Tianyu Zheng,
  • Qian Zeng,
  • Jin Mo,
  • Ruosi Liu,
  • Agus Susanto,
  • Weiqi Liu,
  • Wenchao Guo,
  • Xinhua Ding,
  • Xiaolei Huang,
  • Ding Yang,
  • Daifeng Cheng,
  • Xin Yu,
  • Fan Jiang,
  • Xuankun Li

摘要

Accurate and rapid identification of quarantine-significant tephritids is critical to global agricultural biosecurity, but the application of deep learning is limited by the lack of large public image datasets. We present Tephritid26, a multi-angle image dataset of 26 tephritid species to address this gap. The dataset includes 38,081 images from 1,473 specimens across seven genera and two subfamilies, assembled through a global collaborative effort to source these regulated species. Specimens were mounted using a novel protocol combining varied thoracic attachment points and pin angles, and a rotational imaging setup then systematically captured each specimen from multiple perspectives to mimic real inspection conditions. The dataset is formatted for machine learning workflows. To demonstrate its utility, we trained deep learning models for species identification. ResNet-50, ConvNeXt-B, Vit-Small and Swin-Tiny all attained high species-level accuracy (Macro-Averaged F1-score > 96.75). Gradient-weighted Class Activation Mapping confirmed that the models focused on taxonomically informative morphological regions. This dataset serves as a benchmark for developing automated identification tools in phytosanitary applications.