Scale-Adaptive Face Detection and Tracking in Real Time with SSR Filters and Support Vector Machine
Scale-Adaptive Face Detection and Tracking in Real Time with SSR Filters and Support Vector Machine
复制标题
使用 SSR 滤波器和支持向量机进行实时比例自适应人脸检测和跟踪
DOI：
10.1093/ietisy/e88-d.12.2857
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
K. Hosaka
中科院分区：
文献类型：
--
作者：
S. Kawato;N. Tetsutani;K. Hosaka
本文提出了一种在视频序列中真实的实时检测和跟踪人脸的方法。它可以应用于广泛的面部尺度。我们的基本策略是快速提取人脸候选人的六段矩形（SSR）过滤器和人脸验证的支持向量机。运动提示以简单的方式使用，以避免在背景中拾取错误的候选。在人脸跟踪中，在更新匹配模板的同时跟踪眼睛之间的模式。为了科普各种尺度的人脸，我们使用一系列约1/102的缩小图像，并根据眼睛之间的距离选择适当的尺度。我们测试了我们的算法在7146个视频帧的新闻广播具有手语在320 × 240帧大小，其中一个或两个人出现。虽然手势常常会隐藏面部并中断跟踪，但89%的面部被正确跟踪。我们在一台配有Xeon 2.2-GHz CPU的PC上实现了该系统，运行速度为15帧/秒，无需任何特殊硬件。
In this paper, we propose a method for detecting and tracking faces in video sequences in real time. It can be applied to a wide range of face scales. Our basic strategy for detection is fast extraction of face candidates with a Six-Segmented Rectangular (SSR) filter and face verification by a support vector machine. A motion cue is used in a simple way to avoid picking up false candidates in the background. In face tracking, the patterns of between-the-eyes are tracked while updating the matching template. To cope with various scales of faces, we use a series of approximately 1/√2 scale-down images, and an appropriate scale is selected according to the distance between the eyes. We tested our algorithm on 7146 video frames of a news broadcast featuring sign language at 320 × 240 frame size, in which one or two persons appeared. Although gesturing hands often hid faces and interrupted tracking, 89% of faces were correctly tracked. We implemented the system on a PC with a Xeon 2.2-GHz CPU, running at 15 frames/second without any special hardware.