亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于DXNet模型的富士蘋(píng)果外部品質(zhì)分級(jí)方法研究
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類(lèi)號(hào):

基金項(xiàng)目:

國(guó)家自然科學(xué)基金項(xiàng)目(61902339)、陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃項(xiàng)目(2021JM-418)、延安大學(xué)博士科研啟動(dòng)項(xiàng)目(YDBK2019-06)、延安市科技專(zhuān)項(xiàng)項(xiàng)目(2019-01、2019-13)、谷歌支持教育部產(chǎn)學(xué)合作協(xié)同育人項(xiàng)目(202002107065)和延安大學(xué)大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計(jì)劃項(xiàng)目(S202010719116、DCZX2019-02、S202010719068)


External Quality Grading Method of Fuji Apple Based on Deep Learning
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪(fǎng)問(wèn)統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    針對(duì)傳統(tǒng)計(jì)算機(jī)視覺(jué)技術(shù)在蘋(píng)果外部品質(zhì)分級(jí)中準(zhǔn)確率較低、魯棒性較差等問(wèn)題,提出了基于深度學(xué)習(xí)的蘋(píng)果外觀分級(jí)方法(多卷積神經(jīng)網(wǎng)絡(luò)融合DXNet模型)。首先,在延安市超市、果園等場(chǎng)所實(shí)地拍攝不同外觀等級(jí)的蘋(píng)果圖像15000幅,并進(jìn)行人工標(biāo)記,建立了外部品質(zhì)信息覆蓋度廣、樣本量大的蘋(píng)果圖像數(shù)據(jù)庫(kù);然后,在對(duì)比分析經(jīng)典卷積網(wǎng)絡(luò)模型的基礎(chǔ)上,采用模型融合的方式對(duì)經(jīng)典模型進(jìn)行優(yōu)化改進(jìn),抽取經(jīng)典模型卷積部分進(jìn)行融合,作為特征提取器,共享全連接層用作分類(lèi)器,并采用批歸一化和正則化技術(shù)防止模型過(guò)擬合。試驗(yàn)評(píng)估采用15000幅圖像進(jìn)行訓(xùn)練、4500幅圖像進(jìn)行測(cè)試,結(jié)果表明,DXNet模型的分級(jí)準(zhǔn)確率高于經(jīng)典模型,分級(jí)準(zhǔn)確率達(dá)到97.84%,驗(yàn)證了本文方法用于蘋(píng)果外部品質(zhì)分級(jí)的有效性。

    Abstract:

    The research and development of high-precision and low-cost apple intelligent grading technology is the core issue to extend the apple industrial chain and improve the quality and efficiency of the fruit industry. In order to solve the problems of low accuracy and weak robustness of traditional computer vision technology in apple external quality classification, an apple appearance classification method based on deep learning (multiple convolutional neural network DXNet model) was proposed. Firstly, totally 15000 apple images covering different appearance levels were taken in Yan’an supermarkets, orchards and other places, and then labeled manually. A database of apple images with extensive coverage of external quality information and large sample size was established. Then, on the basis of comparing and analyzing the classical convolution network model, the classical model was optimized and improved by the method of model fusion, and the convolution part of the classical model was extracted and fused to be the feature extractor, and the fully connected layer was shared to be the classifier, batch normalization and regularization techniques were used to prevent the model from over fitting. Totally 15000 images were used for training and 4500 images were used for testing. The results showed that the classification accuracy of the improved DXNet model was higher than that of the classical model, and the classification accuracy reached 97.84%, the validity of the method applied to apple external quality classification was verified.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

何進(jìn)榮,石延新,劉斌,何東健.基于DXNet模型的富士蘋(píng)果外部品質(zhì)分級(jí)方法研究[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2021,52(7):379-385. HE Jinrong, SHI Yanxin, LIU Bin, HE Dongjian. External Quality Grading Method of Fuji Apple Based on Deep Learning[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(7):379-385.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2020-08-18
  • 最后修改日期:
  • 錄用日期:
  • 在線(xiàn)發(fā)布日期: 2021-07-10
  • 出版日期: