Presentation 2018-11-06
Improvement of Laparoscopic Color Image Diagnosis for Automatic Detection of Coded Defect Region and Application of Effective Classifier Parameter
Norifumi Kawabata, Toshiya Nakaguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In addition to judgment by human eyes up to the present, it is advanced for R&D of diagnostic imaging systems by using artificial intelligence positively. Particularly, from informatics, medical engineering field, it is needed for the automatic diagnosis based on image processing to achieve laparoscopic surgery support. Compared to images in the engineering field, it is difficult in the medical images for quantitative judgment and assessment of the coded defect and degradation. Therefore, we also need to consider color information including human visual characteristics and the application of classifier parameter for image information. In this study, first we judged using PSNR whether we can detect the coded defect or not after processing of H.265/HEVC for the certain region in frame images cut from laparoscopic video acquired using endoscopy. Next, we analyzed color information using S-CIELAB color space. Finally, we applied classifier parameter effectively, and discussed for medical image diagnosis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Peak Signal to Noise Ratio / S-CIELAB Color Space / CIEDE2000 / Support Vector Machine
Paper # MICT2018-42,MI2018-42
Date of Issue 2018-10-30 (MICT, MI)

Conference Information
Committee MICT / MI
Conference Date 2018/11/6(1days)
Place (in Japanese) (See Japanese page)
Place (in English) University of Hyogo
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinsuke Hara(Osaka City Univ.) / Kensaku Mori(Nagoya Univ.)
Vice Chair Chika Sugimoto(Yokohama National Univ.) / Eisuke Hanada(Saga Univ.) / Yoshiki Kawata(Tokushima Univ.) / Yuichi Kimura(Kinki Univ.)
Secretary Chika Sugimoto(Nagoya Inst. of Tech.) / Eisuke Hanada(Meiji Univ.) / Yoshiki Kawata(Aichi Inst. of Tech.) / Yuichi Kimura(Nagoya Inst. of Tech.)
Assistant Takumi Kobayashi(Yokohama National Univ.) / Shintaro Izumi(Kobe Univ.) / Ami Tanaka(Ritsumeikan Univ.) / Keita Saku(Kyushu Univ.) / Ryo Haraguchi(Univ. of Hyogo) / Yasushi Hirano(Yamaguchi Univ.)

Paper Information
Registration To Technical Committee on Healthcare and Medical Information Communication Technology / Technical Committee on Medical Imaging
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Improvement of Laparoscopic Color Image Diagnosis for Automatic Detection of Coded Defect Region and Application of Effective Classifier Parameter
Sub Title (in English)
Keyword(1) Peak Signal to Noise Ratio
Keyword(2) S-CIELAB Color Space
Keyword(3) CIEDE2000
Keyword(4) Support Vector Machine
1st Author's Name Norifumi Kawabata
1st Author's Affiliation Nagoya University(Nagoya Univ.)
2nd Author's Name Toshiya Nakaguchi
2nd Author's Affiliation Chiba University(Chiba Univ.)
Date 2018-11-06
Paper # MICT2018-42,MI2018-42
Volume (vol) vol.118
Number (no) MICT-285,MI-286
Page pp.pp.21-26(MICT), pp.21-26(MI),
#Pages 6
Date of Issue 2018-10-30 (MICT, MI)