无需编程，科研人员用AI平台快速构建高精度木材识别模型。
Advancing Wood Identification in the Philippines: Utilizing the Xylorix Platform for Efficient AI Model Development and Deployment for Five Key Species
- 使用Xylorix平台，非程序员也能训练木材识别模型。
- 五种菲律宾硬木识别准确率均超90%，最高达1.000。
- 适合林业执法、海关等一线人员在野外快速识别木材。
非法采伐和木材交易持续威胁菲律宾，准确识别木材种类对执法至关重要，但受限于专业设备与知识。本研究评估了非程序员能否通过Xylorix平台开发并部署宏观木材识别AI模型，针对五种菲律宾硬木：Mangium（Acacia mangium Willd.）、Rain Tree（Samanea saman (Jacq.) Merr.）、Banuyo（Wallaceodendron celebicum Koord.）、Tindalo（Afzelia rhomboidea (Blanco) Vidal）和Ipil（Intsia bijuga (Colebr.) O. Kuntze）。基于260个标本的10,663张验证横截面图像训练二分类器，以标本级平均得分模拟实际场景。AUC值介于0.969（Ipil）至1.000（Mangium），AP值介于0.589（Samanea）至1.000（Mangium）。四类物种达到AA级（AUC与AP均≥0.90）；因正样本仅3个，Rain Tree为AE级（AUC≥0.90，AP<0.60）。所有模型均能近乎完美区分目标与非目标标本。标本级错误分析发现，Ipil有9个假阴性，主要源于局部图像伪影；Rain Tree和Tindalo各有3个和1个假阳性，源于同族水平解剖特征相似。结果表明，非程序员可借助Xylorix平台构建适用于供应链检查点现场部署的可靠木材识别模型。
原文摘要 · Abstract (English)
Illegal logging and timber trade continue to pose significant challenges in the Philippines, where accurate wood species identification is essential for enforcement but limited by the need for specialised equipment and expertise. This study aims to evaluate whether AI models for macroscopic wood identification can be developed and deployed by wood scientists without programming expertise using the Xylorix platform, focusing on five Philippine hardwood species: Mangium (Acacia mangium Willd.), Rain Tree [Samanea saman (Jacq.) Merr.], Banuyo (Wallaceodendron celebicum Koord.), Tindalo [Afzelia rhomboidea (Blanco) Vidal], and Ipil [Intsia bijuga (Colebr.) O. Kuntze]. Binary classifiers were trained on 10,663 verified cross-section images from 260 specimens and evaluated using specimen-level mean scoring to mirror operational field conditions. Area Under the ROC Curve (AUC) values ranged from 0.969 (Ipil) to 1.000 (Mangium), and Average Precision (AP) values ranged from 0.589 (Samanea) to 1.000 (Mangium). Four of five species achieved AA grade (AUC and AP both \geq 0.90); Rain Tree received AE (AUC \geq 0.90, AP < 0.60) due to AP compression from its small positive test set (3 specimens). All five classifiers rank their target specimens above non-target specimens with near-perfect fidelity. Specimen-level error analysis revealed 9 false negatives from Ipil, primarily stemming from localized image artifacts and 3 false positives for Rain Tree and 1 false positive for Tindalo caused by shared tribal-level anatomical traits. These findings demonstrate that Xylorix non-programmers can leverage the Xylorix platform to construct operationally reliable wood identification models suitable for field deployment at supply chain checkpoints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。