醉酒后少妇被疯狂内射视频,一本色道久久综合一,在线天堂新版资源www在线下载,中文字幕乱人伦高清视频,中字幕视频在线永久在线观看免费

Archive > Volume 15 Issue 3 > 2023,15(3):447-456. DOI:https://doi.org/10.1016/j.chmed.2023.01.001 Prev Next

基于深度學(xué)習(xí)的缺陷紅參在線(xiàn)自動(dòng)分選系統(tǒng)

Original articles

An online automatic sorting system for defective Ginseng Radix et Rhizoma Rubra using deep learning

  • Article
  • Figures
  • Metrics
  • Preview PDF
  • Reference
  • Related
  • Cited by
  • Materials
    摘要:
    目的:建立一種基于更快區(qū)域卷積神經(jīng)網(wǎng)絡(luò)(faster R-CNN)算法的深度學(xué)習(xí)架構(gòu)，用于在線(xiàn)x射線(xiàn)機(jī)器視覺(jué)系統(tǒng)對(duì)紅參(參根)內(nèi)部缺陷的自動(dòng)檢測(cè)和分類(lèi)。 方法:采用約2萬(wàn)個(gè)樣本，以0.95的平均精度值(mAP)訓(xùn)練基于R-CNN的快速分類(lèi)器。傳統(tǒng)的基于前饋神經(jīng)網(wǎng)絡(luò)(FNN)的圖像處理方法準(zhǔn)確率、召回率和特異性分別為69.0%、68.0%和70.0%，效果不佳。因此，保存Faster R-CNN模型，評(píng)價(jià)模型在缺陷紅參在線(xiàn)分揀系統(tǒng)上的性能。 結(jié)果:以2000份獨(dú)立的紅參為樣本，通過(guò)3個(gè)平行測(cè)試驗(yàn)證了基于Faster R-CNN的在線(xiàn)分選系統(tǒng)的性能，分選準(zhǔn)確率分別達(dá)到95.8%、95.2%和96.2%。 結(jié)論:基于Faster R-CNN的分類(lèi)模型在紅參內(nèi)部缺陷的無(wú)損檢測(cè)中具有較大的應(yīng)用潛力。

    Abstract:
    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.

    關(guān)鍵詞:
    深度學(xué)習(xí);機(jī)器學(xué)習(xí);無(wú)損檢測(cè);紅參(參根);X-射線(xiàn)

    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).

    Clc Number:

WeChat

Mobile website