Contained neural style transfer for decorated logo generation

Gantugs Atarsaikhan, Brian Kenji Iwana, Seiichi Uchida

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Making decorated logos requires image editing skills, without sufficient skills, it could be a time-consuming task. While there are many on-line web services to make new logos, they have limited designs and duplicates can be made. We propose using neural style transfer with clip art and text for the creation of new and genuine logos. We introduce a new loss function based on distance transform of the input image, which allows the preservation of the silhouettes of text and objects. The proposed method contains style transfer to only a designated area. We demonstrate the characteristics of proposed method. Finally, we show the results of logo generation with various input images.

Original languageEnglish
Title of host publicationProceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages317-322
Number of pages6
ISBN (Electronic)9781538633465
DOIs
Publication statusPublished - Jun 22 2018
Event13th IAPR International Workshop on Document Analysis Systems, DAS 2018 - Vienna, Austria
Duration: Apr 24 2018Apr 27 2018

Publication series

NameProceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

Other

Other13th IAPR International Workshop on Document Analysis Systems, DAS 2018
CountryAustria
CityVienna
Period4/24/184/27/18

Fingerprint

Web services

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Atarsaikhan, G., Iwana, B. K., & Uchida, S. (2018). Contained neural style transfer for decorated logo generation. In Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018 (pp. 317-322). (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DAS.2018.78

Contained neural style transfer for decorated logo generation. / Atarsaikhan, Gantugs; Iwana, Brian Kenji; Uchida, Seiichi.

Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 317-322 (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Atarsaikhan, G, Iwana, BK & Uchida, S 2018, Contained neural style transfer for decorated logo generation. in Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 317-322, 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, Vienna, Austria, 4/24/18. https://doi.org/10.1109/DAS.2018.78
Atarsaikhan G, Iwana BK, Uchida S. Contained neural style transfer for decorated logo generation. In Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 317-322. (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018). https://doi.org/10.1109/DAS.2018.78
Atarsaikhan, Gantugs ; Iwana, Brian Kenji ; Uchida, Seiichi. / Contained neural style transfer for decorated logo generation. Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 317-322 (Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018).
@inproceedings{d98c4f67c8c84ca2bee708aa4f71432a,
title = "Contained neural style transfer for decorated logo generation",
abstract = "Making decorated logos requires image editing skills, without sufficient skills, it could be a time-consuming task. While there are many on-line web services to make new logos, they have limited designs and duplicates can be made. We propose using neural style transfer with clip art and text for the creation of new and genuine logos. We introduce a new loss function based on distance transform of the input image, which allows the preservation of the silhouettes of text and objects. The proposed method contains style transfer to only a designated area. We demonstrate the characteristics of proposed method. Finally, we show the results of logo generation with various input images.",
author = "Gantugs Atarsaikhan and Iwana, {Brian Kenji} and Seiichi Uchida",
year = "2018",
month = "6",
day = "22",
doi = "10.1109/DAS.2018.78",
language = "English",
series = "Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "317--322",
booktitle = "Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018",
address = "United States",

}

TY - GEN

T1 - Contained neural style transfer for decorated logo generation

AU - Atarsaikhan, Gantugs

AU - Iwana, Brian Kenji

AU - Uchida, Seiichi

PY - 2018/6/22

Y1 - 2018/6/22

N2 - Making decorated logos requires image editing skills, without sufficient skills, it could be a time-consuming task. While there are many on-line web services to make new logos, they have limited designs and duplicates can be made. We propose using neural style transfer with clip art and text for the creation of new and genuine logos. We introduce a new loss function based on distance transform of the input image, which allows the preservation of the silhouettes of text and objects. The proposed method contains style transfer to only a designated area. We demonstrate the characteristics of proposed method. Finally, we show the results of logo generation with various input images.

AB - Making decorated logos requires image editing skills, without sufficient skills, it could be a time-consuming task. While there are many on-line web services to make new logos, they have limited designs and duplicates can be made. We propose using neural style transfer with clip art and text for the creation of new and genuine logos. We introduce a new loss function based on distance transform of the input image, which allows the preservation of the silhouettes of text and objects. The proposed method contains style transfer to only a designated area. We demonstrate the characteristics of proposed method. Finally, we show the results of logo generation with various input images.

UR - http://www.scopus.com/inward/record.url?scp=85050317618&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050317618&partnerID=8YFLogxK

U2 - 10.1109/DAS.2018.78

DO - 10.1109/DAS.2018.78

M3 - Conference contribution

AN - SCOPUS:85050317618

T3 - Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

SP - 317

EP - 322

BT - Proceedings - 13th IAPR International Workshop on Document Analysis Systems, DAS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -