Neural Network-Based Chinese Ink-Painting Art Style Learning

摘要：

For purposes of intelligent art creation and existed painting style reusing, we presents a neural networkbased Chinese ink-painting art style learning method, which is quite different from the traditional pixel-wise or sample-wise style transferring work. We first give a generalized definition for style features of Chinese ink painting, and then establish the style learning mechanisms with combination of back propagation neural network and image analysis techniques. The paralyzed global style features from input painting are analyzed by the well trained style learning system, the learning outputs are extracted from style information library for Chinese painting. The experiment results show that the method works well, and it is obviously a new exploration for painting style learning.

关键词： Chinese Ink-Painting Artistic Style Learning BP Neural Networks Texture Analyses Image Segmentation

作者: Zheng Wang Meijun Sun Jizhou Sun Peng Lv

作者单位: Tianjin University School of Computer Software Tianjin, China Tianjin University School of Computer Science and Technology Tianjin, China

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 462-466

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）