摘要
风格转移技术能快速生成目标艺术作品,但直接用在中国画上通常会存在特征分布不协调、人脸辨识不一致等问题.针对上述问题,文中提出基于卷积神经网络(CNN)的中国肖像画风格转移算法.首先,针对中国肖像画中写意和工笔两种绘画技法,提出笔触控制约束,指导图像的纹理分布.然后,提出国画特征移动距离,用于度量内容与风格特征,并将参考的中国画风格协调部署在肖像照上.最后,针对中国画的水墨色调和留白特点,提出水墨留白约束改进损失网络.实验表明,文中算法生成的结果不仅保证人脸辨识的一致性,而且在中国画艺术风格上表现更优.
Style transfer algorithms can generate target artworks quickly.However,the problems are caused by applying style transfer algorithms directly to Chinese paintings,like uneven feature distribution and inconsistent face recognition.To address these issues,a Chinese portrait painting style transfer algorithm based on convolutional neural network(CNN)is proposed.Firstly,a brushstroke control restriction is proposed to guide the texture distribution of the image for freehand brushwork and fine brushwork of Chinese portrait painting.Then,Chinese painting moving distance is proposed to measure content and style features and transfer the style of Chinese painting to portrait photos harmoniously.Finally,the restriction for improving the loss network is put forward based on the ink tone characteristics and the blank space reservation.Experiments show that the proposed algorithm is superior in Chinese painting style and the results maintain the consistency of face recognition.
作者
盛家川
董玙璠
李小妹
李玉芝
SHENG Jiachuan;DONG Yufan;LI Xiaomei;LI Yuzhi(School of Science and Technology,Tianjin University of Finance and Economics,Tianjin 300222;Department of Sci-tech Innovation and Achievement Transformation,Tianjin University of Finance and Economics,Tianjin 300222)
出处
《模式识别与人工智能》
CSCD
北大核心
2021年第6期509-521,共13页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.61502331)
教育部人文社科项目(No.18YJA630057,19YJA630046)
天津市自然科学基金项目(No.18JCYBJC85100)资助。
关键词
风格转移
中国肖像画
卷积神经网络
笔触控制约束
国画特征移动距离
水墨留白约束
Style Transfer
Chinese Portrait Painting
Convolutional Neural Network
Brushstroke Control Restriction
Chinese Painting Moving Distance
Ink and Space Reservation Restriction
