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 intern...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 20000 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%,and70.0%,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.展开更多
基金funded by National Natural Science Foundation of China(Grant No.82074276)Projects of International Cooperation of Traditional Chinese Medicine(Grant No.06102040NF020928)+1 种基金National S&T Major Project of China(Grant No.2018ZX09201011)Innovation Team and Talents Cultivation Program of National Administration of Traditional Chinese Medicine.(No.ZYYCXTD-D-202002)。
文摘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 20000 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%,and70.0%,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.
