系统仿真学报 ›› 2015, Vol. 27 ›› Issue (10): 2305-2309.

• 人工智能与仿真 • 上一篇    下一篇

复杂背景下发型轮廓的自动提取方法

金遥力1, 王世亮1, 徐岗1, 胡维华1, 王毅刚2   

  1. 1.杭州电子科技大学计算机学院,杭州 310018;
    2.杭州电子科技大学数字媒体与艺术设计学院,杭州 310018
  • 收稿日期:2015-06-30 修回日期:2015-08-03 出版日期:2015-10-08 发布日期:2020-08-07
  • 作者简介:金遥力(1993-),男,浙江杭州人,硕士生,研究方向为计算机图形图像处理;王世亮(1990-),男,山东临沂人,硕士,研究方向为图像处理与可视化。
  • 基金资助:
    国家自然科学基金面上项目(61472111); 浙江大学CAD&CG国家重点实验室开放课题(A1406); 浙江省自然科学基金(LR16F020003)

Automatic Hair Contour Extraction Method with Complex Background

Jin Yaoli1, Wang Shiliang1, Xu Gang1, Hu Weihua1, Wang Yigang2   

  1. 1. Department of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China;
    2. Department of Media and Arts, Hangzhou Diazi University, Hangzhou 310018, China
  • Received:2015-06-30 Revised:2015-08-03 Online:2015-10-08 Published:2020-08-07

摘要: 发型轮廓提取在数字娱乐仿真中具有重要应用。提出了一种复杂背景下发型轮廓的自动提取方法框架。对图像进行前景图像进行分割,从而去除背景图像对发型提取结果的干扰;通过人脸识别技术进行发型定位,进一步结合头发检测技术以实现发型的自动识别;为提高轮廓抽取的准确度,通过自适应皮肤检测以去除人脸对于发型轮廓提取的干扰。将本文方法应用于大量实例,实验结果表明:该方法不仅可以有效的自动提取发型轮廓,而且对于复杂背景下的发型轮廓提取也有具有良好效果。

关键词: 发型轮廓, 自动提取, 图像分割, 人脸检测, 复杂背景

Abstract: Hair contour extraction has important application in digital entertainment and simulation. An automatic hair contour extraction method for images with complex background was proposed. Image segmentation algorithm from foreground image was used to eliminate the interference of background image; face recognition and hair detection algorithms were employed to find the hair position and realize the automatic identification of the hair; in order to improve the accuracy of contour extraction, adaptive skin detection algorithm was used to eliminate the interference of face. The proposed method was applied on a lot of image examples. Experimental results demonstrate that this method can automatically extract hair contour effectively, and it also works well for some examples with complex background.

Key words: hair contour, automatic extraction, image segmentation, face detection, complex background

中图分类号: