欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 视觉与图像 • 上一篇    下一篇

基于卷积神经网络的中国水墨画风格提取

  

  1. 1. 南京大学电子科学与工程学院，江苏 南京 210023；
    2. 江苏省公安厅物证鉴定中心，江苏 南京 210031；
    3. 南通市肿瘤医院放疗科，江苏 南通 226361
  • 出版日期:2017-10-31 发布日期:2017-11-03
  • 基金资助:
    2015年江苏省政策引导类计划(产学研合作)-前瞻性联合研究项目(BY2015069-06)；2016年度省重点研发计划-社会发展-临床前沿技术
    (SBE2016750075)

Convolutional Neural Network-Based Chinese Ink-Painting Artistic Style Extraction

  1. 1. School of Electronic Science and Engineering, Nanjing University, Nanjing Jiangsu 210023, China;
    2. Jiangsu Province Public Security Bureau Material Identification Center, Nanjing Jiangsu 210031, China;
    3. Radiotherapy Department, Nantong Cancer Hospital, Nantong Jiangsu 226361, China
  • Online:2017-10-31 Published:2017-11-03

PDF (PC)

472

摘要： 针对使用卷积神经网络对中国水墨画风格进行学习的过程进行了探讨。首先，分
析了 VGG19 神经网络模型的框架结构，并探讨了如何使用 VGG19 模型提取艺术风格，并和普
通风景图像融合的过程；然后，在理论的基础上，依据中国水墨画的实际特点，通过实验分析
寻找合适的卷积层处理内容图像，以及寻找最优的叠加组合对水墨画特征进行提取，并提出了
评价图像质量的可视化准则；最后，通过调整内容图像和风格图像的比例系数，得到了符合预
期目标的图像，验证了理论的可行性，提出了新的中国水墨画风格图像的风格提取方法。

关键词: 卷积神经网络, 中国水墨画, 艺术风格学习, 特征提取

Abstract: This paper discusses the process of Chinese ink-painting style learning using convolution
neural network. Firstly, the frame structure of VGG19 neural network model is analyzed, and the
process of using VGG19 model to separate and recombine the content and style of artistic images.
Secondly, based on the theory, according to the actual characteristics of Chinese ink painting, the
appropriate choice of the convoluted layer to process the content image is found and proved by
experimental results. The optimal combination of convoluted layer to extract the style from Chinese
ink painting is also found by experiment, and the criteria for visual evaluation of image quality are
proposed. Finally, by adjusting the proportion coefficient of the content image and the style image,
the expected combined image can be obtained, which verifies the feasibility of the theory and puts
forward a new method for Chinese ink-painting style extraction.

Key words: convolutional neural network, Chinese ink-painting, artistic style learning, feature
extraction