Presentation | 2022-06-09 [Invited Talk] Advanced applications of machine learning techniques towards high-performance and cost-effective visual inspection AI Terumasa Tokunaga, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Visual inspection is an essential step for quality control in manufacturing. Recently, many researchers have shown great interest in the establishment of visual inspection AI driven by breakthroughs in deep learning. Supervised approaches require the large number of defective and defect-free sample images for training classifiers. However, in many practical situations, the collection of defective images is quite costly. We are now developing novel anomaly detection techniques towards cost-effective and high-performance visual inspection AI. Our approaches rely on advanced application of machine learning techniques, including unsupervised learning, semi-supervised learning and visual attention mechanism. This presentation will report the current status and scope of our projects including recent collaborative researches with manufacturing companies. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | visual inspection AI / anomaly detection / deep neural network / generative adversarial network / visual attention mechanism / semi-supervised learning |
Paper # | SIS2022-6 |
Date of Issue | 2022-06-02 (SIS) |
Conference Information | |
Committee | SIS / IPSJ-AVM |
---|---|
Conference Date | 2022/6/9(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | KIT(Wakamatsu Campus) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Intelligent Multimedia Systems, Applied Embedded Systems, Three-Dimensional Image Technology (3DIT), etc. |
Chair | Noriaki Suetake(Yamaguchi Univ.) / Sei Naito(KDDI Research, Inc.) |
Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) |
Secretary | Tomoaki Kimura(NTT) / Naoto Sasaoka(National Inst. of Tech., Ube College) / (NTT) |
Assistant | Soh Yoshida(Kansai Univ.) / Yoshiaki Makabe(Kanagawa Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Smart Info-Media Systems / Special Interest Group on Audio Visual and Multimedia Information Processing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Invited Talk] Advanced applications of machine learning techniques towards high-performance and cost-effective visual inspection AI |
Sub Title (in English) | |
Keyword(1) | visual inspection AI |
Keyword(2) | anomaly detection |
Keyword(3) | deep neural network |
Keyword(4) | generative adversarial network |
Keyword(5) | visual attention mechanism |
Keyword(6) | semi-supervised learning |
1st Author's Name | Terumasa Tokunaga |
1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
Date | 2022-06-09 |
Paper # | SIS2022-6 |
Volume (vol) | vol.122 |
Number (no) | SIS-62 |
Page | pp.pp.30-30(SIS), |
#Pages | 1 |
Date of Issue | 2022-06-02 (SIS) |