Presentation 2017-10-12
[Short Paper] A Study on Manga Object Recognition Mechanism by Convolution Neural Network
Hideaki Yanagisawa, Takuro Yamashita, Hiroshi Watanabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to make use of manga images on the internet, techniques to detect objects such as speech balloons and character faces and to create metadata have been studied. At this time, a method of collectively detecting for variety manga objects is important. In previous research, we confirmed that object detection method using Convolutional Neural Network has effectiveness for manga objects. In this paper, we examine the detection results for manga objects in various forms, and examine the mechanism of CNN detectors to recognize manga objects with various shapes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CNN / Faster R-CNN / manga / object detetion
Paper # PRMU2017-79
Date of Issue 2017-10-05 (PRMU)

Conference Information
Committee PRMU
Conference Date 2017/10/12(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] A Study on Manga Object Recognition Mechanism by Convolution Neural Network
Sub Title (in English)
Keyword(1) CNN
Keyword(2) Faster R-CNN
Keyword(3) manga
Keyword(4) object detetion
1st Author's Name Hideaki Yanagisawa
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Takuro Yamashita
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Hiroshi Watanabe
3rd Author's Affiliation Waseda University(Waseda Univ.)
Date 2017-10-12
Paper # PRMU2017-79
Volume (vol) vol.117
Number (no) PRMU-238
Page pp.pp.93-94(PRMU),
#Pages 2
Date of Issue 2017-10-05 (PRMU)