ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2019-02-20 16:15
[Invited Talk] Automatic Gaze Correction based on Deep Learning and Image Warping
Masataka Seo, Yamamoto Takahiro (Ritsumeikan Univ), Toshihiro Kitajima (Samsung), Chen Yen-Wei (Ritsumeikan Univ)
Abstract (in Japanese) (See Japanese page) 
(in English) When people take a selfie photo or talk through a video chat system, they tend to look at the screen. Since the position of the camera is usually different from that of the screen, the eyes of the person in the photograph or transmitted live video seem to make contact with something other than the viewer. This paper proposes a method to correct the gaze by synthesizing the image texture. The image synthesis uses feature points around the eyes as landmarks. A common convolutional neural network and long-term recurrent convolution network are used to extract or detect these feature points in a still image and video image, respectively. The deep learning-based feature point detections are very accurate compared to conventional methods. These feature points are used as landmarks, and the internal texture of these feature points are synthesized with the prepared template image in advance. Through these procedures, an automatic and natural gaze correction is realized. This method realized a natural gaze correction with little blur, even for a video image.
Keyword (in Japanese) (See Japanese page) 
(in English) gaze correction / image synthesis / convolutional neural network / long-term recurrent convolution networks / / / /  
Reference Info. ITE Tech. Rep., vol. 43, no. 5, ME2019-47, pp. 255-259, Feb. 2019.
Paper # ME2019-47 
Date of Issue 2019-02-12 (MMS, HI, ME, AIT) 
ISSN Print edition: ISSN 1342-6893    Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2019-02-19 - 2019-02-20 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2019-02-ME-IE-ITS-MMS-HI-AIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Automatic Gaze Correction based on Deep Learning and Image Warping 
Sub Title (in English)  
Keyword(1) gaze correction  
Keyword(2) image synthesis  
Keyword(3) convolutional neural network  
Keyword(4) long-term recurrent convolution networks  
1st Author's Name Masataka Seo  
1st Author's Affiliation Ritsumeikan University (Ritsumeikan Univ)
2nd Author's Name Yamamoto Takahiro  
2nd Author's Affiliation Ritsumeikan University (Ritsumeikan Univ)
3rd Author's Name Toshihiro Kitajima  
3rd Author's Affiliation Samsung R&D Institute Japan (Samsung)
4th Author's Name Chen Yen-Wei  
4th Author's Affiliation Ritsumeikan University (Ritsumeikan Univ)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2019-02-20 16:15:00 
Presentation Time 15 minutes 
Registration for ME 
Paper # MMS2019-25, HI2019-25, ME2019-47, AIT2019-25 
Volume (vol) vol.43 
Number (no) no.5 
Page pp.255-259 
Date of Issue 2019-02-12 (MMS, HI, ME, AIT) 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan