完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Lai, Yu-Ting Kevin | en_US |
dc.contributor.author | Hu, Jwu-Sheng | en_US |
dc.date.accessioned | 2019-04-02T06:04:36Z | - |
dc.date.available | 2019-04-02T06:04:36Z | - |
dc.date.issued | 2018-01-01 | en_US |
dc.identifier.issn | 1062-922X | en_US |
dc.identifier.uri | http://dx.doi.org/10.1109/SMC.2018.00736 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/151111 | - |
dc.description.abstract | Surface defect detection is challenging due to varying defect types and defect novelties. Because of this, it is hard for algorithms to implement across datasets. Moreover, current automated optical inspection (AOI) machines cannot handle this novelty effectively. In this work, we develop a new method for surface defect detection based on generative models, which can detect novelty according to learned distributions. Experimental results on real industrial datasets show that the proposed method can successfully construct the surface texture pattern generator. By transforming the image through the generator to the corresponding latent space, the defects can be separated effectively without a tedious effort of annotation in a large amount of training data. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | automated optical inspection | en_US |
dc.subject | surface defect detection | en_US |
dc.subject | generative adversarial networks | en_US |
dc.title | A Texture Generation Approach for Detection of Novel Surface Defects | en_US |
dc.type | Proceedings Paper | en_US |
dc.identifier.doi | 10.1109/SMC.2018.00736 | en_US |
dc.identifier.journal | 2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) | en_US |
dc.citation.spage | 4343 | en_US |
dc.citation.epage | 4348 | en_US |
dc.contributor.department | 電機工程學系 | zh_TW |
dc.contributor.department | Department of Electrical and Computer Engineering | en_US |
dc.identifier.wosnumber | WOS:000459884804057 | en_US |
dc.citation.woscount | 0 | en_US |
顯示於類別: | 會議論文 |