College of Pharmaceutical Engineering of Traditional Chinese Medicine, Tianjin University of Traditional Chinese Medicine, Tianjin, China.
State Key Laboratory of Component Traditional Chinese Medicine, Tianjin, China.
J Food Sci. 2022 Aug;87(8):3386-3395. doi: 10.1111/1750-3841.16237. Epub 2022 Jul 5.
An online machine learning system based on X-ray nondestructive quality evaluation technique was developed to detect internal defects of boat-fruited sterculia seed. The X-ray images of boat-fruited sterculia seed were first acquired by the detection system. Then, a boat-fruited sterculia seed net (BSSNet) was trained to identify the defective boat-fruited sterculia seeds based on the X-ray images. The BSSNet was evaluated with the accuracy, precision, specificity, and sensitivity as 94.64%, 93.51%, 92.37%, and 96.64%, respectively. Further, three classical CNN models including VGG16, Resnet, and Inception were trained on the same dataset with accuracy of 95.71%, 94.29%, and 94.64%, respectively. Compared with the classical CNN models, the BSSNet achieved similar or higher accuracy in X-ray images classification. Finally, an independent dataset containing 200 X-ray images was used to validate the performance of the BSSNet and obtained an accuracy of 96.5%. The results presented above demonstrated that this classification method has a great potential for industrial applications. PRACTICAL APPLICATION: An X-ray online detection system integrated with a machine vision model was used to evaluate the quality of boat-fruited sterculia seed. A low-power x-ray detection system can detect internal defects of the object and ensure safety in the production process. The developed machine vision can sort the boat-fruited sterculia seed with an accuracy of 96.5%. The proposed nondestructive detection system showed a good potential to be used in industrial applications.
基于 X 射线无损质量评价技术的在线机器学习系统被开发用于检测酸豆种子的内部缺陷。首先通过检测系统获取酸豆种子的 X 射线图像，然后基于 X 射线图像训练酸豆种子网络（BSSNet）来识别有缺陷的酸豆种子。BSSNet 的准确率、精确率、特异性和灵敏度分别为 94.64%、93.51%、92.37%和 96.64%。此外，三个经典的 CNN 模型，包括 VGG16、Resnet 和 Inception，在相同的数据集上进行了训练，准确率分别为 95.71%、94.29%和 94.64%。与经典的 CNN 模型相比，BSSNet 在 X 射线图像分类方面达到了相似或更高的准确率。最后，使用包含 200 张 X 射线图像的独立数据集来验证 BSSNet 的性能，准确率为 96.5%。结果表明，该分类方法在工业应用中具有很大的潜力。实际应用：将机器视觉模型与 X 射线在线检测系统集成，用于评估酸豆种子的质量。低功率 X 射线检测系统可以检测物体的内部缺陷，并确保生产过程的安全性。开发的机器视觉可以以 96.5%的准确率对酸豆种子进行分类。所提出的无损检测系统在工业应用中具有很好的应用潜力。
