Presentation | 2019-03-15 Estimation of dislocation regions in multicrystalline silicon photoluminescence image by transfer learning with convolutional neural network Hiroaki Kudo, Tetsuya Matsumoto, Kentaro Kutsukake, Noritaka Usami, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, we studied a specified method of regions including dislocations which are crystallographic defects in a photoluminescence (PL) image of multicrystalline silicon wafers. We applied transfer learning of a convolutional neural network to archive it. The network outputs the category which includes dislocation regions or one which does not include them. High accuracies of more than 0.94 are realized. It outperformed methods of multilayer perceptron which has up to 3 hidden layers or of bag of features algorithm as an index by Youden's index. It also obtained better results than the method using non-negative matrix factorization in the condition that the image has larger in depth of learning images in the silicon ingot. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | convolutional neural network / transfer learning / multicrystalline silicon / photoluminescence image / dislocation |
Paper # | IMQ2018-69,IE2018-153,MVE2018-100 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |
Conference Information | |
Committee | IMQ / IE / MVE / CQ |
---|---|
Conference Date | 2019/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kagoshima University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | media of five senses, multimedia, media experience, picture codinge, image media quality, network,quality and reliability, etc |
Chair | Kenji Sugiyama(Seikei Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Kenji Mase(Nagoya Univ.) / Takanori Hayashi(Hiroshima Inst. of Tech.) |
Vice Chair | Toshiya Nakaguchi(Chiba Univ.) / Mitsuru Maeda(Canon) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(NEC) / Jun Okamoto(NTT) |
Secretary | Toshiya Nakaguchi(Nagoya Univ.) / Mitsuru Maeda(Sony) / Hideaki Kimata(KDDI Research) / Kazuya Kodama(Nagoya Univ.) / Masayuki Ihara(NTT) / Hideyuki Shimonishi(Kyushu Univ.) / Jun Okamoto(Nagoya Univ.) |
Assistant | Masaru Tsuchida(NTT) / Gosuke Ohashi(Shizuoka Univ.) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK) / Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(*) / Chikara Sasaki(KDDI Research) / Yoshiaki Nishikawa(NEC) / Ryo Yamamoto(UEC) |
Paper Information | |
Registration To | Technical Committee on Image Media Quality / Technical Committee on Image Engineering / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Communication Quality |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Estimation of dislocation regions in multicrystalline silicon photoluminescence image by transfer learning with convolutional neural network |
Sub Title (in English) | |
Keyword(1) | convolutional neural network |
Keyword(2) | transfer learning |
Keyword(3) | multicrystalline silicon |
Keyword(4) | photoluminescence image |
Keyword(5) | dislocation |
1st Author's Name | Hiroaki Kudo |
1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
2nd Author's Name | Tetsuya Matsumoto |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Kentaro Kutsukake |
3rd Author's Affiliation | RIKEN(RIKEN) |
4th Author's Name | Noritaka Usami |
4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2019-03-15 |
Paper # | IMQ2018-69,IE2018-153,MVE2018-100 |
Volume (vol) | vol.118 |
Number (no) | IMQ-500,IE-501,MVE-502 |
Page | pp.pp.257-262(IMQ), pp.257-262(IE), pp.257-262(MVE), |
#Pages | 6 |
Date of Issue | 2019-03-07 (IMQ, IE, MVE) |