Fan Xiangpeng, Zhou Jianping
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China.
Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing 100081, China.
Foods. 2025 Jul 1;14(13):2346. doi: 10.3390/foods14132346.
The internal quality detection is extremely important. To solve the challenges of walnut quality detection, we presented the first comprehensive investigation of walnut quality detection method using X-ray imaging and deep learning model. An X-ray machine vision system was designed, and a walnut kernel detection (called WKD) dataset was constructed. Then, an effective walnut kernel detection network (called WKNet) was developed by employing Transformer, GhostNet, and criss-cross attention (called CCA) module to the YOLO v5s model, aiming to solve the time consuming and parameter redundancy issues. The WKNet achieved an mAP_0.5 of 0.9869, precision of 0.9779, and recall of 0.9875 for walnut kernel detection. The inference time per image is only 11.9 ms. Extensive comparison experiments with the state-of-the-art (SOTA) deep learning models demonstrated the advanced nature of WKNet. The online test of walnut internal quality detection also shows satisfactory performance. The innovative combination of X-ray imaging and WKNet provide significant implications for walnut quality control.
内部质量检测极其重要。为解决核桃质量检测面临的挑战，我们首次对基于X射线成像和深度学习模型的核桃质量检测方法进行了全面研究。设计了一个X射线机器视觉系统，并构建了一个核桃仁检测（称为WKD）数据集。然后，通过将Transformer、GhostNet和交叉注意力（称为CCA）模块应用于YOLO v5s模型，开发了一种有效的核桃仁检测网络（称为WKNet），旨在解决耗时和参数冗余问题。WKNet在核桃仁检测中实现了0.9869的mAP_0.5、0.9779的精度和0.9875的召回率。每张图像的推理时间仅为11.9毫秒。与最先进的（SOTA）深度学习模型进行的广泛比较实验证明了WKNet的先进性。核桃内部质量检测的在线测试也显示出令人满意的性能。X射线成像和WKNet的创新结合对核桃质量控制具有重要意义。
Zotero 插件
