摘要
随着计算机技术的快速发展,人脸检测已经应用到各个领域,但是依然存在在低光照和有遮挡等复杂背景下人脸检测率低的问题,针对这一问题,文章提出了一种基于概率加权的AdaBoost与YCrCb颜色空间算法相结合的人脸检测方法。文章使用Haar-like矩形特征作为人脸特征的提取算法,将概率加权的AdaBoost算法与改进的YCrCb颜色空间算法相结合提高人脸检测的检测率。实验证明,在不同光照下、不同角度以及面部遮挡下的情况下,文章提出的算法可以在提高检测率的同时,大幅度地降低计算的复杂度。
With the rapid development of computer technology,face detection has been applied to various fields,but there are still problems of low face detection rate in complex backgrounds such as low light and occlusion.Aiming at the problem,this paper proposes a face detection method based on probability-weighted AdaBoost and YCrCb color space algorithm.Haarlike rectangular features are used as the extraction algorithm for face features in this paper,and the probability-weighted AdaBoost algorithm is combined with the improved YCrCb color space algorithm to improve the detection rate of face detection.Experiments show that the algorithm proposed in this paper can greatly reduce the complexity of the calculation while improving the detection rate under the conditions with different light,different angles and face occlusion.
作者
马文亭
姜楠楠
MA Wenting;JIANG Nannan(Harbin Huade University,Harbin 150025,China)
出处
《现代信息科技》
2025年第3期79-83,89,共6页
Modern Information Technology
基金
2024年度黑龙江省教育科学规划重点课题(GJB1424364)。
