Presentation | 2018-09-21 [Short Paper] Stroke Recovery of Handwritten Chinese Character using Fully Convolutional Networks Wang Yu Jung, Motoharu Sonogashira, Atsushi Hashimoto, Masaaki Iiyama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose a method to recover strokes from offline handwritten Chinese characters. The proposed method employs multitask fully convolutional networks (FCN) to estimate writing order and direction of strokes from offline character images. Online data in CASIA database is used for training. Since the FCN produces discontinuous strokes, our method refines the estimation of the writing order by using a graph cut (GC). Experimental results with test dataset of CASIA-OLHWDB1.0 show the effectiveness of our method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Handwriting Trajectory Recovery / Semantic Segmentation / Convolutional Networks / Deep Learning |
Paper # | PRMU2018-62,IBISML2018-39 |
Date of Issue | 2018-09-13 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IBISML / IPSJ-CVIM |
---|---|
Conference Date | 2018/9/20(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Hisashi Kashima(Kyoto Univ.) |
Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Short Paper] Stroke Recovery of Handwritten Chinese Character using Fully Convolutional Networks |
Sub Title (in English) | |
Keyword(1) | Handwriting Trajectory Recovery |
Keyword(2) | Semantic Segmentation |
Keyword(3) | Convolutional Networks |
Keyword(4) | Deep Learning |
1st Author's Name | Wang Yu Jung |
1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
2nd Author's Name | Motoharu Sonogashira |
2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
3rd Author's Name | Atsushi Hashimoto |
3rd Author's Affiliation | OMRON SINICX Corporation(Omron SINICX) |
4th Author's Name | Masaaki Iiyama |
4th Author's Affiliation | Kyoto University(Kyoto Univ.) |
Date | 2018-09-21 |
Paper # | PRMU2018-62,IBISML2018-39 |
Volume (vol) | vol.118 |
Number (no) | PRMU-219,IBISML-220 |
Page | pp.pp.157-162(PRMU), pp.157-162(IBISML), |
#Pages | 6 |
Date of Issue | 2018-09-13 (PRMU, IBISML) |