复杂光照环境下视频人脸序列的自动检测方法  

Automatic Face Detection in Video Sequences in Complex Lighting Environments

作　　者：谢倩茹[1] 耿国华[1] 

机构地区：[1]西北大学信息科学与技术学院,西安710127

出　　处：《计算机科学》2011年第10期267-269,共3页Computer Science

基　　金：国家自然科学基金重点项目(60873094);国家高技术研究发展计划(863)(2008AA01Z301)资助

摘　　要：基于视频序列人脸自动检测是人脸跟踪、识别等研究的基础。提出了一种结合图像增强技术、gabor特征变换和adaboost算法的视频序列人脸检测方法,其主要思想是使用图像增强技术对图像进行光照补偿,减轻不同的光照条件(如局部的阴影和高亮等)对检测结果的影响。该方法首先通过高频增强滤波强化图像的边缘和细节信息,用基于直方图的技术来调节图像的亮度,然后应用gabor小波变换进行特征抽取,最后采用adaboost方法训练样本,完成人脸的检测。实验表明,该方法能够在不同的光照条件下准确检测出人脸,显示出较强的鲁棒性。Auto human face detection from video sequences is the base of studies for human face recognition and tracking.This paper proposed an efficient and robust method to detect face in vido sequences.The key step of this work is to use the technique of image enhancement to alleviate the impact of human face detection caused by variation illumination such as local shadow and highlight.The approach firstly strengthens the edge and detail information of images by means of high-frequency enhanced filtering and uses histogram-based technique to adjust the brightness of the image,then applies the Gabor wavelet to extract features of images,finally trains samples using the adaboost algorithm and complete face detection.The experimental results show that the approach can detect human face accurately under different lighting conditions.

关 键 词：人脸检测 图像增强 光照补偿 GABOR小波 ADABOOST 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]