Presentation 2022-05-20
少数豚画像からGANにより生成された画像を用いて訓練された深層学習を用いた豚足切断箇所の推定法
Kanda Koki, Onuki Ryo, Ohkawauchi Takaaki, Ohya Jun,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) n this paper, GAN learning was performed using a dataset of live-action pig images taken in the previous year to generate a large number of elaborate pig images, and it was verified whether the generated images could be a substitute for the live-action pig images. After performing Semantic Segmentation training using only the generated pig images as the dataset, we used the training data to recognize the joints and hooves of the front feet in the live-action pig images taken last year, and calculated the cut-off coordinates and angles of the cut-off front feet. The calculated values were compared with the values calculated using the training data from the live-action images, and the errors were evaluated. The results of the estimation using the training data from the live-action pig image and the estimation using the training data from the generated pig image confirm that the pig image generated by StyleGAN2 can be a substitute for the live-action pig image.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) GAN / StyleGAN2 / DCGAN / Semantic Segmentation / cutting porkleg
Paper # SIP2022-19,BioX2022-19,IE2022-19,MI2022-19
Date of Issue 2022-05-12 (SIP, BioX, IE, MI)

Conference Information
Committee SIP / BioX / IE / MI / ITE-IST / ITE-ME
Conference Date 2022/5/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kumamoto University Kurokami Campus
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yukihiro Bandou(NTT) / Hitoshi Imaoka(NEC) / Kazuya Kodama(NII) / Hidekata Hontani(Nagoya Inst. of Tech.)
Vice Chair Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(SECOM) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Hideaki Haneishi(Chiba Univ.) / Takayuki Kitasaka(Aichi Inst. of Tech.)
Secretary Toshihisa Tanaka(Xiaomi) / Takayuki Nakachi(Takushoku Univ.) / Masatsugu Ichino(Tokyo Univ. Agri.&Tech.) / Naoyuki Takada(KDDI Research) / Hiroyuki Bandoh(MitsubishiElectric) / Toshihiko Yamazaki(KDDI Research) / Hideaki Haneishi(Nagoya Inst. of Tech.) / Takayuki Kitasaka(Yamaguchi Univ.) / (Univ. of Hyogo)
Assistant Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Hiroyuki Suzuki(Gunma Univ) / Akihiro Hayasaka(NEC) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Hotaka Takizawa(Tsukuba Univ.) / Yoshito Otake(NAIST)

Paper Information
Registration To Technical Committee on Signal Processing / Technical Committee on Biometrics / Technical Committee on Image Engineering / Technical Committee on Medical Imaging / Technical Group on Information Sensing Technologies / Technical Group on Media Engineering
Language JPN-ONLY
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1) GAN
Keyword(2) StyleGAN2
Keyword(3) DCGAN
Keyword(4) Semantic Segmentation
Keyword(5) cutting porkleg
1st Author's Name Kanda Koki
1st Author's Affiliation Waseda University(Waswda Univ)
2nd Author's Name Onuki Ryo
2nd Author's Affiliation Waseda University(Waswda Univ)
3rd Author's Name Ohkawauchi Takaaki
3rd Author's Affiliation Nihon University(Nihon Univ)
4th Author's Name Ohya Jun
4th Author's Affiliation Waseda University(Waswda Univ)
Date 2022-05-20
Paper # SIP2022-19,BioX2022-19,IE2022-19,MI2022-19
Volume (vol) vol.122
Number (no) SIP-28,BioX-29,IE-30,MI-31
Page pp.pp.97-102(SIP), pp.97-102(BioX), pp.97-102(IE), pp.97-102(MI),
#Pages 6
Date of Issue 2022-05-12 (SIP, BioX, IE, MI)