计算机应用 ›› 2010, Vol. 30 ›› Issue (3): 635-638.

• 图形图像处理 • 上一篇    下一篇

复杂背景下的多人脸检测方法

苑玮琦1,韩春霞2   

  1. 1.
    2. 沈阳工业大学,视觉检测技术研究所
  • 收稿日期:2009-09-28 修回日期:2009-11-19 发布日期:2010-03-14 出版日期:2010-03-01
  • 通讯作者: 韩春霞
  • 基金资助:
    人眼自然张开状态下虹膜识别方法的研究

Multi-face detection algorithm in complex background

  • Received:2009-09-28 Revised:2009-11-19 Online:2010-03-14 Published:2010-03-01

摘要: 复杂背景下采用肤色进行人脸检测具有较高的检测率,但同时也具有较高的误检率,而采用AdaBoost算法进行人脸检测从根本上解决了实时性问题,但是检测率不理想。基于上述原因,采用肤色分割与AdaBoost相结合的方法对人脸进行检测:首先采用肤色分割进行人脸粗定位,然后将粗定位后的人脸候选区域作为AdaBoost检测的输入子窗口进行人脸检测。在预处理过程中,采用可调节结构元素,解决了对于不同图像中大小不一的人脸采用固定的结构元素造成的人脸丢失问题。实验结果表明该方法在提高检测率的同时,也降低了误检率。

关键词: 人脸检测, 肤色分割, 可调节的结构元素, AdaBoost算法, 级联分类器

Abstract: Face detection based on skin color has a higher detection rate, but it also has a higher false detection rate. AdaBoost face detection algorithm is a fundamental solution to the real-time issue, but its detection rate is not satisfactory. For these reasons, the algorithm that combined skin color division and AdaBoost method was proposed. Firstly, color division was used for rough location of human faces, and after that the candidate region was put as the input of AdaBoost face detection window. In the pretreatment processing, the structure of adjustable elements was used to solve the problem that the human faces were lost because of the different size in the different images. The experimental results show that the proposed method improves the detection rate and also reduces the false rate.

Key words: face detection, skin color division, adjustable structural element, AdaBoost algorithm, cascade classifier