Abstract
In the Panax notoginseng quality intelligent management system, the big roots and fibrous roots cannot be cut automatically because the machine cannot distinguish the taproot, big roots, and fibrous roots of Panax notoginseng, resulting in the automatic cutting mechanism unable to obtain the control trajectory coordinate reference of the tool feed. To solve this problem, this paper proposes a visual optimal network model detection method, which uses the image detection method of marking anchor frames to improve the detection accuracy. A variety of deep learning network models are modified by the TensorFlow framework, and the best training model is optimized by comparing the results of training, testing, and verification data. This model is used to automatically identify the taproots and provide the control trajectory coordinate reference for the actuator that cuts big roots and fibrous roots automatically. The experimental results show that the optimal network model studied in this paper is effective and accurate in identifying the taproots of Panax notoginseng.
Highlights
Introduction ePanax notoginseng industry is an important component of Yunnan province in China. e Yunnan Panax notoginseng processing plant needs to process a big amount of Panax notoginseng raw materials in harvest season. ese raw materials will be powdered or sliced to prepare them for use in subsequent pharmaceuticals
Model Performance Comparison. is paper used different deep learning network models to detect the taproot of Panax notoginseng
To better realize the comparison of various network models and select the optimal network model, this paper proposed a comprehensive performance verification formula that combines average accuracy, accuracy, missed detection rate, and false detection rate for deep learning model performance evaluation and comparison. e verification formula is shown in (6), where Hp is the number of the taproots of Panax notoginseng predicted by the deep learning model, Ht is the sample size of the real Panax notoginseng taproot, Hl is the number of missed detections of the taproot of Panax notoginseng, and Hf is the number of errors during the detection
Summary
Is paper used different deep learning network models to detect the taproot of Panax notoginseng. To better realize the comparison of various network models and select the optimal network model, this paper proposed a comprehensive performance verification formula that combines average accuracy, accuracy, missed detection rate, and false detection rate for deep learning model performance evaluation and comparison. Panax notoginseng taproot detection was to perform image detection on the verification set according to the optimal model trained in deep learning. The test platform was used, and the industrial tablet computer was used to embed the optimal network model to realize the detection and result display of the images collected by the industrial camera. The loss function curve of the SSD _ Lite _ mobilenet _ v2 _coco model was in a state of nonconvergence, and the loss functions of SSD _ Lite _ mobilenet _ v2 _ coco and SSD_ inception _v2_coco were
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
