The contour image style-transfer-based convolutional neural network

Nan Deng, Jing Li, Xingce Wang, Zhongke Wu, Yan Fu, Wuyang Shui, Mingquan Zhou, Vladimir Korkhov, Luciano Paschoal Gaspary

Research outputpeer-review

Abstract

The aim of style transfer is giving the style from one picture to another. The application of neural network in image processing separates the high level features and low level features of the image in the process of style transfer, and derives a variety of methods and optimization for style processing. The style transfer generates new images by separating and recombining the content and style of original images. In this process, various factors such as color and illumination will affect the result. The traditional algorithm only focuses on continuous pixels and the whole image, this paper will extend the process object to the contour of the image, and improves the detail processing from the existing style transfer examples. From the contour of images, the target image retains the contour feature of style image and the content of original image, in other word, gives the contour style of style image to original image. Finally, the style transfer effect based on the original image contour is obtained with some defects. The work can be easily extended to the aspects of video and 3D images.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Image Technology, IWAIT 2019
EditorsPhooi Yee Lau, Yung-Lyul Lee, Kazuya Hayase, Lu Yu, Sanun Srisuk, Qian Kemao, Wen-Nung Lie
PublisherSPIE
ISBN (Electronic)9781510627734
DOIs
Publication statusPublished - 1 Jul 2019
EventInternational Workshop on Advanced Image Technology 2019, IWAIT 2019 - Singapore
Duration: 6 Jan 20199 Jan 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11049
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceInternational Workshop on Advanced Image Technology 2019, IWAIT 2019
CountrySingapore
CitySingapore
Period6/01/199/01/19

Fingerprint

Neural Networks
Neural networks
Processing
Image processing
Lighting
Pixels
Color
Defects
Style
3D Image
Illumination
Image Processing
image processing
Pixel
illumination
pixels
color
Target
Optimization
optimization

Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Deng, N., Li, J., Wang, X., Wu, Z., Fu, Y., Shui, W., ... Gaspary, L. P. (2019). The contour image style-transfer-based convolutional neural network. In P. Y. Lau, Y-L. Lee, K. Hayase, L. Yu, S. Srisuk, Q. Kemao, & W-N. Lie (Eds.), International Workshop on Advanced Image Technology, IWAIT 2019 [110493C] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11049). SPIE. https://doi.org/10.1117/12.2521489
Deng, Nan ; Li, Jing ; Wang, Xingce ; Wu, Zhongke ; Fu, Yan ; Shui, Wuyang ; Zhou, Mingquan ; Korkhov, Vladimir ; Gaspary, Luciano Paschoal. / The contour image style-transfer-based convolutional neural network. International Workshop on Advanced Image Technology, IWAIT 2019. editor / Phooi Yee Lau ; Yung-Lyul Lee ; Kazuya Hayase ; Lu Yu ; Sanun Srisuk ; Qian Kemao ; Wen-Nung Lie. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{6b066eb4d26b414c9979bb92434b9a29,
title = "The contour image style-transfer-based convolutional neural network",
abstract = "The aim of style transfer is giving the style from one picture to another. The application of neural network in image processing separates the high level features and low level features of the image in the process of style transfer, and derives a variety of methods and optimization for style processing. The style transfer generates new images by separating and recombining the content and style of original images. In this process, various factors such as color and illumination will affect the result. The traditional algorithm only focuses on continuous pixels and the whole image, this paper will extend the process object to the contour of the image, and improves the detail processing from the existing style transfer examples. From the contour of images, the target image retains the contour feature of style image and the content of original image, in other word, gives the contour style of style image to original image. Finally, the style transfer effect based on the original image contour is obtained with some defects. The work can be easily extended to the aspects of video and 3D images.",
keywords = "contour processing, convolutional neural network, deep learning, style transfer",
author = "Nan Deng and Jing Li and Xingce Wang and Zhongke Wu and Yan Fu and Wuyang Shui and Mingquan Zhou and Vladimir Korkhov and Gaspary, {Luciano Paschoal}",
year = "2019",
month = "7",
day = "1",
doi = "10.1117/12.2521489",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Lau, {Phooi Yee} and Yung-Lyul Lee and Kazuya Hayase and Lu Yu and Sanun Srisuk and Qian Kemao and Wen-Nung Lie",
booktitle = "International Workshop on Advanced Image Technology, IWAIT 2019",
address = "United States",

}

Deng, N, Li, J, Wang, X, Wu, Z, Fu, Y, Shui, W, Zhou, M, Korkhov, V & Gaspary, LP 2019, The contour image style-transfer-based convolutional neural network. in PY Lau, Y-L Lee, K Hayase, L Yu, S Srisuk, Q Kemao & W-N Lie (eds), International Workshop on Advanced Image Technology, IWAIT 2019., 110493C, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11049, SPIE, Singapore, 6/01/19. https://doi.org/10.1117/12.2521489

The contour image style-transfer-based convolutional neural network. / Deng, Nan; Li, Jing; Wang, Xingce; Wu, Zhongke; Fu, Yan; Shui, Wuyang; Zhou, Mingquan; Korkhov, Vladimir; Gaspary, Luciano Paschoal.

International Workshop on Advanced Image Technology, IWAIT 2019. ed. / Phooi Yee Lau; Yung-Lyul Lee; Kazuya Hayase; Lu Yu; Sanun Srisuk; Qian Kemao; Wen-Nung Lie. SPIE, 2019. 110493C (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11049).

Research outputpeer-review

TY - GEN

T1 - The contour image style-transfer-based convolutional neural network

AU - Deng, Nan

AU - Li, Jing

AU - Wang, Xingce

AU - Wu, Zhongke

AU - Fu, Yan

AU - Shui, Wuyang

AU - Zhou, Mingquan

AU - Korkhov, Vladimir

AU - Gaspary, Luciano Paschoal

PY - 2019/7/1

Y1 - 2019/7/1

N2 - The aim of style transfer is giving the style from one picture to another. The application of neural network in image processing separates the high level features and low level features of the image in the process of style transfer, and derives a variety of methods and optimization for style processing. The style transfer generates new images by separating and recombining the content and style of original images. In this process, various factors such as color and illumination will affect the result. The traditional algorithm only focuses on continuous pixels and the whole image, this paper will extend the process object to the contour of the image, and improves the detail processing from the existing style transfer examples. From the contour of images, the target image retains the contour feature of style image and the content of original image, in other word, gives the contour style of style image to original image. Finally, the style transfer effect based on the original image contour is obtained with some defects. The work can be easily extended to the aspects of video and 3D images.

AB - The aim of style transfer is giving the style from one picture to another. The application of neural network in image processing separates the high level features and low level features of the image in the process of style transfer, and derives a variety of methods and optimization for style processing. The style transfer generates new images by separating and recombining the content and style of original images. In this process, various factors such as color and illumination will affect the result. The traditional algorithm only focuses on continuous pixels and the whole image, this paper will extend the process object to the contour of the image, and improves the detail processing from the existing style transfer examples. From the contour of images, the target image retains the contour feature of style image and the content of original image, in other word, gives the contour style of style image to original image. Finally, the style transfer effect based on the original image contour is obtained with some defects. The work can be easily extended to the aspects of video and 3D images.

KW - contour processing

KW - convolutional neural network

KW - deep learning

KW - style transfer

UR - http://www.scopus.com/inward/record.url?scp=85063877037&partnerID=8YFLogxK

U2 - 10.1117/12.2521489

DO - 10.1117/12.2521489

M3 - Conference contribution

AN - SCOPUS:85063877037

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Workshop on Advanced Image Technology, IWAIT 2019

A2 - Lau, Phooi Yee

A2 - Lee, Yung-Lyul

A2 - Hayase, Kazuya

A2 - Yu, Lu

A2 - Srisuk, Sanun

A2 - Kemao, Qian

A2 - Lie, Wen-Nung

PB - SPIE

ER -

Deng N, Li J, Wang X, Wu Z, Fu Y, Shui W et al. The contour image style-transfer-based convolutional neural network. In Lau PY, Lee Y-L, Hayase K, Yu L, Srisuk S, Kemao Q, Lie W-N, editors, International Workshop on Advanced Image Technology, IWAIT 2019. SPIE. 2019. 110493C. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2521489