基于生成对抗网络和Mask R-CNN的苹果早期变质检测
[目的]提高苹果早期变质区的检测准确率.[方法]基于生成对抗网络和卷积神经网络技术的苹果变质区检测方法.利用Pix2PixHD模型生成包含采后早期变质区的贮藏苹果的近红外成像数据;使用Mask R-CNN模型对生成的近红外图像进行分割,以检测苹果中的变质区;在具有人工智能功能的低成本嵌入式系统上,利用生成的近红外成像数据,实施基于生成对抗网络和卷积神经网络技术的采后苹果的早期变质区域分割和预测.[结果]该方法对收获后苹果的早期变质检测平均准确率比其他9种方法高1.825％～10.435％;Pix2PixHD能以17帧/s的速度从RGB图像生成了可视近红外图像,Mask R-CNN能够以4.2帧...
Saved in:
| Published in | 食品与机械 Vol. 40; no. 6; pp. 143 - 169 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
河北机电职业技术学院,河北 邢台 054000%河北科技大学,河北 石家庄 050018%河北农业大学,河北保定 071001
01.06.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1003-5788 |
| DOI | 10.13652/j.spjx.1003.5788.2024.60038 |
Cover
| Abstract | [目的]提高苹果早期变质区的检测准确率.[方法]基于生成对抗网络和卷积神经网络技术的苹果变质区检测方法.利用Pix2PixHD模型生成包含采后早期变质区的贮藏苹果的近红外成像数据;使用Mask R-CNN模型对生成的近红外图像进行分割,以检测苹果中的变质区;在具有人工智能功能的低成本嵌入式系统上,利用生成的近红外成像数据,实施基于生成对抗网络和卷积神经网络技术的采后苹果的早期变质区域分割和预测.[结果]该方法对收获后苹果的早期变质检测平均准确率比其他9种方法高1.825％～10.435％;Pix2PixHD能以17帧/s的速度从RGB图像生成了可视近红外图像,Mask R-CNN能够以4.2帧/s的速度对苹果图像中的变质区域进行分割.[结论]研究提出的方法有望促进低成本食品质量控制器的开发. |
|---|---|
| AbstractList | [目的]提高苹果早期变质区的检测准确率.[方法]基于生成对抗网络和卷积神经网络技术的苹果变质区检测方法.利用Pix2PixHD模型生成包含采后早期变质区的贮藏苹果的近红外成像数据;使用Mask R-CNN模型对生成的近红外图像进行分割,以检测苹果中的变质区;在具有人工智能功能的低成本嵌入式系统上,利用生成的近红外成像数据,实施基于生成对抗网络和卷积神经网络技术的采后苹果的早期变质区域分割和预测.[结果]该方法对收获后苹果的早期变质检测平均准确率比其他9种方法高1.825％～10.435％;Pix2PixHD能以17帧/s的速度从RGB图像生成了可视近红外图像,Mask R-CNN能够以4.2帧/s的速度对苹果图像中的变质区域进行分割.[结论]研究提出的方法有望促进低成本食品质量控制器的开发. |
| Abstract_FL | [Objective]To improve the detection accuracy of early apple spoilage zone.[Methods]An apple spoilage detection method was proposed based on generative adversarial network and convolutional neural network.The Pix2PixHD model was used to generate near-infrared imaging data of stored apples in the early postharvest metamorphic area.The Mask R-CNN model was used to segment the generated near Infrared image to detect the deterioration zone in the apple.Based on generative adversarial network and convolutional neural network technology,the early deterioration region segmentation and prediction of postharvest apples were implemented by using the generated near-infrared imaging data on a low-cost embedded system with artificial intelligence function.[Results]The average accuracy of this method was 1.825％～10.435％higher than that of the other nine methods.The Pix2PixHD generated a visible NIR image from an RGB image at 17 frames per second,and the Mask R-CNN was able to segment spoilage areas in an apple image at 4.2 frames per second.[Conclusion]The proposed method is expected to facilitate the development of low-cost food quality controllers. |
| Author | 赵晓东 于琦龙 籍宇 孙尧 王春荣 |
| AuthorAffiliation | 河北机电职业技术学院,河北 邢台 054000%河北科技大学,河北 石家庄 050018%河北农业大学,河北保定 071001 |
| AuthorAffiliation_xml | – name: 河北机电职业技术学院,河北 邢台 054000%河北科技大学,河北 石家庄 050018%河北农业大学,河北保定 071001 |
| Author_FL | YU Qilong ZHAO Xiaodong JI Yu WANG Chunrong SUN Yao |
| Author_FL_xml | – sequence: 1 fullname: YU Qilong – sequence: 2 fullname: ZHAO Xiaodong – sequence: 3 fullname: JI Yu – sequence: 4 fullname: WANG Chunrong – sequence: 5 fullname: SUN Yao |
| Author_xml | – sequence: 1 fullname: 于琦龙 – sequence: 2 fullname: 赵晓东 – sequence: 3 fullname: 籍宇 – sequence: 4 fullname: 王春荣 – sequence: 5 fullname: 孙尧 |
| BookMark | eNotj7tKA0EYhaeIYIx5Bwux2_Wf-Wd2Zztl8QYxgmgdZm_iKpvgIGpnYRGMeEOISDCFjVY2WiTi27izeQwTtDqcr_gOZ4aUsmYWEzJPwaboCLaY2rqVntoUAG3hSmkzYNx2xlWWSHmCrQmeJlWt9wNAhyP3HCyTpbw__BleFw99077N3wfmslt83xVfvfz-alPpg7lty6_Xi6eLUWdgnnum-2Z6_fzmcfTxal7OzWdnlkwl6lDH1f-skN3VlR1_3aptrW34yzVLU6BgUS_2ABgTCU8SFsYhV4KCJ2MUGFDqoAzRVegGjMvYhShCyT0RqEgoJmQSYYUs_HlPVJaobK-RNo-PsvFiQ7fO0nTyFxxggL8JnWFW |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.13652/j.spjx.1003.5788.2024.60038 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Early spoilage detection of apple based on generative adversarial network and Mask R-CNN |
| EndPage | 169 |
| ExternalDocumentID | spyjj202406020 |
| GrantInformation_xml | – fundername: (河北省高等学校科学技术研究项目); (邢台市科技计划自筹经费项目) funderid: (河北省高等学校科学技术研究项目); (邢台市科技计划自筹经费项目) |
| GroupedDBID | -02 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS CCEZO CDRFL GROUPED_DOAJ PSX TCJ |
| ID | FETCH-LOGICAL-s1010-19e900225f4ff2cec4a51098e353b11638c37a37b248e70dd38495bad5a258fd3 |
| ISSN | 1003-5788 |
| IngestDate | Thu May 29 03:54:44 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Keywords | generative adversarial network apple 生成对抗网络 苹果 卷积神经网络 early spoilage detection 早期变质检测 convolutional neural network 图像转换 image conversion |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1010-19e900225f4ff2cec4a51098e353b11638c37a37b248e70dd38495bad5a258fd3 |
| PageCount | 27 |
| ParticipantIDs | wanfang_journals_spyjj202406020 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-06-01 |
| PublicationDateYYYYMMDD | 2024-06-01 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 食品与机械 |
| PublicationTitle_FL | Food & Machinery |
| PublicationYear | 2024 |
| Publisher | 河北机电职业技术学院,河北 邢台 054000%河北科技大学,河北 石家庄 050018%河北农业大学,河北保定 071001 |
| Publisher_xml | – name: 河北机电职业技术学院,河北 邢台 054000%河北科技大学,河北 石家庄 050018%河北农业大学,河北保定 071001 |
| SSID | ssib036434963 ssib001105548 ssib001214864 ssj0002912145 ssib002263614 ssib008679503 ssib051376485 ssib000271415 |
| Score | 2.3855186 |
| Snippet | [目的]提高苹果早期变质区的检测准确率.[方法]基于生成对抗网络和卷积神经网络技术的苹果变质区检测方法.利用Pix2PixHD模型生成包含采后早期变质区的贮藏苹果的近红外成像... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 143 |
| Title | 基于生成对抗网络和Mask R-CNN的苹果早期变质检测 |
| URI | https://d.wanfangdata.com.cn/periodical/spyjj202406020 |
| Volume | 40 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 1003-5788 databaseCode: DOA dateStart: 20220101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0002912145 providerName: Directory of Open Access Journals |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Na9RAFA-1gngRRcVve-iclqyZr2TmZpJNKUJ7kFZ6K8luoqywFrcF7cmDB7HiF0JFij140ZMXPbTif-Nm-2f43iTdpLTVKoQwzLy8N7_3hnnz8TJjWZPMw728jNoaple2UElix0JmtkhFzFma6U6KE8WZWXd6XtxakAtj43dqUUsry0mzvXrgfyX_Y1XIA7viX7L_YNkRU8iANNgX3mBheB_JxiSSRE-RwCeRwLeKSOQRLTAzcolSRDtI4wONNjk-0R7SBC2iqUkERIeGDyMqnIn79xu37XB21jACjoJEiqig_F5HhtpFLn6RExphkqgpohUSB4L4Cot8jmEUkAigNKiPgkmksbT4UAMZNQCUAWB4IiTgwEgw2k7Zi9EhvotsAqiRrkgUCoMHuWhkXfDVYUUCmClRLaOXiFR-GEuAOWDFjxXxpYHegprWl0aYqEK4TGM2CKGi3GghNAoeYTDWCApOFEvL-vilNQoFAbFvdOG3SlhQeQDPwv3MG1isGBYXWg-cBg6I8bZteVBdwFKeMfZIIMgRmDkSeIgczzQuXmoqcDGBFhAgEK9ZPEQgJAykCuqRBBp6aES7ltF-wxwKRWt-E0McofNXdcdanMNVdiB1L0mLk7nKARct7urZ58u5K5lx5v2l7iOM5uFNlNBESzdd3NKuxjCjyNL-0uNuFykcFyZCx6zjDLy9U1tqKXfbaX0ZgeItsbVlAcqo2HNrAXO5W4s2wEMqZRW9wGFUL3R1jJ2k4LVFeSYUjgiZRo7SBF6UejphTe5ivPEHhOZXwl4W9-7WRr1zp61T5XR1wi_6njPW2Oq9s9bNweb2r-2Xw3eb-bPXg69b-fP14c83wx8bg7cvsAeZMD3I8MPTnbWt_ONGvv4l39gcvHq_8-1z_ulJ_n3tnDU_Fc2F03Z5E4vdpyZ8S6ca1SAzkWWsnbZFDL5cq5RLnlCc0rW5F3MvYUKlntPpcCW0TOKOjJlUWYeft8Z7D3rpBWtCMpVokbaVq9vCSZwkieMUD_5LPVCZ8C5a10vEi2VP21_ca9RLf6W4bJ2suoMr1vjyw5X0KswdlpNrpiH8BtULwx4 |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E7%94%9F%E6%88%90%E5%AF%B9%E6%8A%97%E7%BD%91%E7%BB%9C%E5%92%8CMask+R-CNN%E7%9A%84%E8%8B%B9%E6%9E%9C%E6%97%A9%E6%9C%9F%E5%8F%98%E8%B4%A8%E6%A3%80%E6%B5%8B&rft.jtitle=%E9%A3%9F%E5%93%81%E4%B8%8E%E6%9C%BA%E6%A2%B0&rft.au=%E4%BA%8E%E7%90%A6%E9%BE%99&rft.au=%E8%B5%B5%E6%99%93%E4%B8%9C&rft.au=%E7%B1%8D%E5%AE%87&rft.au=%E7%8E%8B%E6%98%A5%E8%8D%A3&rft.date=2024-06-01&rft.pub=%E6%B2%B3%E5%8C%97%E6%9C%BA%E7%94%B5%E8%81%8C%E4%B8%9A%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E6%B2%B3%E5%8C%97+%E9%82%A2%E5%8F%B0+054000%25%E6%B2%B3%E5%8C%97%E7%A7%91%E6%8A%80%E5%A4%A7%E5%AD%A6%2C%E6%B2%B3%E5%8C%97+%E7%9F%B3%E5%AE%B6%E5%BA%84+050018%25%E6%B2%B3%E5%8C%97%E5%86%9C%E4%B8%9A%E5%A4%A7%E5%AD%A6%2C%E6%B2%B3%E5%8C%97%E4%BF%9D%E5%AE%9A+071001&rft.issn=1003-5788&rft.volume=40&rft.issue=6&rft.spage=143&rft.epage=169&rft_id=info:doi/10.13652%2Fj.spjx.1003.5788.2024.60038&rft.externalDocID=spyjj202406020 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fspyjj%2Fspyjj.jpg |