Objective: To establish a deep-learning architecture based on faster region-based convolutional neural networks (Faster R-CNN) algorithm for detection and sorting of red ginseng (Ginseng Radix et Rhizoma Rubra) with internal defects automatically on an online X-ray machine vision system. Methods: A Faster R-CNN based classifier was trained with around 20 000 samples with mean average precision value (mAP) of 0.95. A traditional image processing method based on feedforward neural network (FNN) obtained a bad performance with the accuracy, recall and specificity of 69.0%, 68.0%, and 70.0%, respectively. Therefore, the Faster R-CNN model was saved to evaluate the model performance on the defective red ginseng online sorting system. Results: An independent set of 2000 red ginsengs were used to validate the performance of the Faster RCNN based online sorting system in three parallel tests, achieving accuracy of 95.8%, 95.2% and 96.2%, respectively. Conclusion: The overall results indicated that the proposed Faster R-CNN based classification model has great potential for non-destructive detection of red ginseng with internal defects.
关键词:
深度学习;机器学习;无损检测;红参(参根);X-射线
Keywords:
Project Supported:
This research was funded by National Natural Science Foundation of China (Grant No. 82074276), Projects of International Cooperation of Traditional Chinese Medicine (Grant No. 0610-2040NF020928), National S&T Major Project of China (Grant No. 2018ZX09201011), and Innovation Team and Talents Cultivation Program of National Administration of Traditional Chinese Medicine. (No. ZYYCXTD-D-202002).
Qilong Xuea, b, Peiqi Miaoc, Kunhong Miaoa, b, Yang Yua, b,*, Zheng Lia, b,*. An online automatic sorting system for defective Ginseng Radix et Rhizoma Rubra using deep learning[J]. Chinese Herbal Medicines (CHM),2023,15(3):447-456