计算机与现代化

• 图像处理 • 上一篇    下一篇

一种使用多维度直方图匹配的图像风格迁移算法

  

  1. (上海理工大学光电信息与计算机工程学院,上海200093)
  • 收稿日期:2018-10-19 出版日期:2019-02-25 发布日期:2019-02-26
  • 作者简介:李雨妮(1998-),女,湖南邵阳人,本科生,研究方向:机器学习与计算机视觉,E-mail: 1612020104@st.usst.edu.cn; 通信作者:肖建力(1982-),男,讲师,博士,研究方向:数据挖掘与大数据技术,机器学习与计算机视觉,智能交通与智慧城市,E-mail: audyxiao@sjtu.edu.cn。
  • 基金资助:
    国家自然科学基金资助项目(61603257)

An Image Style Transfer Algorithm Based on Multi-dimension Histograms Matching

  1. (School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China)
  • Received:2018-10-19 Online:2019-02-25 Published:2019-02-26

摘要: 在传统的基于直方图匹配的图像风格迁移算法的基础上,提出一种新的基于多维度直方图匹配的图像风格迁移算法。通过构建关于原图像的不同维度的直方图,然后进行原图像和目标图像的匹配,分别得到原图像在不同维度直方图下的风格迁移图像,最后对这些风格迁移后的图像进行融合生成最终的结果。在保持原图像与目标图像整体风格上尽量相似的情形下,同时又使原图像的局部细节尽可能保留,实现整体风格相似却又保留局部细节的平衡。

关键词: 多维度, 直方图匹配, 风格迁移

Abstract: Based on the classical image style transfer algorithm using histogram matching, a new image style transfer algorithm has been proposed, which uses multi-dimension histograms matching. Firstly, different dimension histograms are generated. Then, the histogram matching is performed between the original and target images. As a result, the images after style transfer using different dimension histograms are obtained. Finally, the image having the same style with the target image is produced by fusing the images obtained in the histogram matching step. Experimental results show that the proposed algorithm can ensure that the original and target images obtain the best similarity in global scale. Meanwhile, the proposed algorithm can also make the generated image save the most details from the original image. Namely, the generated image has the similarity between the original and target images as much as possible and the local details from the original image are saved as many as possible simultaneously.

Key words: multi-dimension, histogram matching, style transfer

中图分类号: