| Presentation | 2018-09-21 Analysis of the Resion of Interest in Visual Inspection using CNN Katsuhisa Kitaguchi, Yohei Nishizaki, Mamoru Saito, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We have been developing a deep learning-based method for automated visual inspection of deep drawing metal products. Deep drawing is a process technology that forms a sheet metal beyond its limits of ordinary stamping, which often suffers from many kinds of surface defects due to lack of material strength, improper lubrication and contamination. So we proposed a CNN model for multi-label classification to find various surface defects and it showed better classification performance than the conventional two class model. Here we examine the regions of interest of both models and the difference of them. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | CNN / Visual inspection / Metal parts |
| Paper # | PRMU2018-59,IBISML2018-36 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2018/9/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Analysis of the Resion of Interest in Visual Inspection using CNN |
| Sub Title (in English) | |
| Keyword(1) | CNN |
| Keyword(2) | Visual inspection |
| Keyword(3) | Metal parts |
| 1st Author's Name | Katsuhisa Kitaguchi |
| 1st Author's Affiliation | Osaka Research Institute of Industrial Science and Technology(ORIST) |
| 2nd Author's Name | Yohei Nishizaki |
| 2nd Author's Affiliation | Osaka Research Institute of Industrial Science and Technology(ORIST) |
| 3rd Author's Name | Mamoru Saito |
| 3rd Author's Affiliation | Osaka Research Institute of Industrial Science and Technology(ORIST) |
| Date | 2018-09-21 |
| Paper # | PRMU2018-59,IBISML2018-36 |
| Volume (vol) | vol.118 |
| Number (no) | PRMU-219,IBISML-220 |
| Page | pp.pp.143-147(PRMU), pp.143-147(IBISML), |
| #Pages | 5 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |