基于人脸特征和线积分卷积的肖像素描生成  

Portrait Drawing Generation Based on Facial Features and Line Integral Convolution

作　　者：赵艳丹[1] 赵汉理[2] 许佳奕[3] 茅晓阳 金小刚[1] 

机构地区：[1]浙江大学CAD&CG国家重点实验室,杭州310058 [2]温州大学智能信息系统研究所,温州325035 [3]杭州电子科技大学计算机学院,杭州310018 [4]Visual Computing Laboratory, University of Yamanashi, Kofu, 400-8511 Japan

出　　处：《计算机辅助设计与图形学学报》2014年第10期1711-1719,共9页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金项目(61472351,61328204)

摘　　要：为了更好地模拟素描的笔画和突显肖像素描中五官的部分,提出基于人脸特征和线积分卷积的肖像素描生成方法.首先进行人脸分割,由人脸特征点确定GrabCut算法中每个特征的初始trimap,然后根据分割结果使用线积分卷积算法绘制肖像素描.文中使用了基于分割结果的多分辨率白噪声和方向场,并提出了基于分割结果的自适应性边界提取算法.实验结果表明,该算法改善了肖像素描的生成效果.To better proposes a portrmt mimic the strokes of portrait drawings and to emphasize facial features, this paper drawing generation method based on face features and line integral convolution （LIC）. Firstly, our method segments the human face, which uses the feature points of the human face to define an initial trimap for the GrabCut algorithm for each feature. Then we render the portrait drawing using LIC according to the segmentation. We utilize multi-scale white noise pyramids and vector field pyramids in LIC and propose an adaptive edge extraction algorithm based on the segmentation. Experimental results demonstrate that our method can improve the quality of portrait drawing.

关 键 词：人脸特征 线积分卷积 非真实感绘制 铅笔画 人物素描 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]