{"product_id":"ieej-st18099","title":"Product Defect Detection Based on Transfer Learning of CNN","description":"\u003cp\u003e\u003cstrong\u003eカテゴリ: \u003c\/strong\u003e研究会(論文単位)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e論文No: \u003c\/strong\u003eST18099\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eグループ名: \u003c\/strong\u003e【C】電子・情報・システム部門 システム研究会\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e発行日: \u003c\/strong\u003e2018\/09\/27\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eタイトル(英語): \u003c\/strong\u003eProduct Defect Detection Based on Transfer Learning of CNN\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名: \u003c\/strong\u003eSu Kai(University of Aizu),Zhao Qiangfu(University of Aizu)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e著者名(英語): \u003c\/strong\u003eKai Su(University of Aizu),Qiangfu Zhao(University of Aizu)\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eキーワード: \u003c\/strong\u003eProduct defect detection|Convolution neural network (CNN)|Image classification|Transfer learning|Product defect detection|Convolution neural network (CNN)|Image classification|Transfer learning\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(日本語): \u003c\/strong\u003eIn this paper, we focus on product surface defect detection. Defect detection is an essential step in a production line. So far, this task has been conducted mainly by human inspectors. The inspection results are often affected by various human factors like inspector’s experiences, health conditions, and so on. To improve the accuracy, in this study we apply the convolution neural network (CNN) to support the human inspector. In recent years, CNN has been applied successfully for image recognition in various fields. In this paper, we investigate several methods based on CNN, and report results obtained through experiments on image datasets provided by our partner company. Results show that both AlexNet and GoogLeNet can recognize surface defect very well with the recognition rates 99.63% and 99.51%, respectively. The proposed system can “reject” a certain percentage of the data and leave them for human-based inspection. In addition, the system can also detect wrongly labeled data or outliers, and thus can help human inspectors to purify the training data.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e要約(英語): \u003c\/strong\u003eIn this paper, we focus on product surface defect detection. Defect detection is an essential step in a production line. So far, this task has been conducted mainly by human inspectors. The inspection results are often affected by various human factors like inspector’s experiences, health conditions, and so on. To improve the accuracy, in this study we apply the convolution neural network (CNN) to support the human inspector. In recent years, CNN has been applied successfully for image recognition in various fields. In this paper, we investigate several methods based on CNN, and report results obtained through experiments on image datasets provided by our partner company. Results show that both AlexNet and GoogLeNet can recognize surface defect very well with the recognition rates 99.63% and 99.51%, respectively. The proposed system can “reject” a certain percentage of the data and leave them for human-based inspection. In addition, the system can also detect wrongly labeled data or outliers, and thus can help human inspectors to purify the training data.\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003e原稿種別: \u003c\/strong\u003e英語\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003ePDFファイルサイズ: \u003c\/strong\u003e1,737 Kバイト\u003c\/p\u003e","brand":"IEEJ-PDF","offers":[{"title":"PDFダウンロード（一般価格330円\/会員価格220円） \/ A4 \/ 4","offer_id":46390749135087,"sku":"IEEJ-ST18099-PDF","price":330.0,"currency_code":"JPY","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0718\/9512\/2159\/files\/IEEJ-PDF_eda875ab-ce87-43ec-8d03-a65f63e7e609.png?v=1744602521","url":"https:\/\/ieej.bookpark.ne.jp\/products\/ieej-st18099","provider":"電気学会 電子図書館","version":"1.0","type":"link"}