中文摘要：

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.

英文摘要：

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.