摘要: AdaBoost人脸检测算法用于嵌入式实时高清视频时检测速度缓慢。为此,提出一种改进的人脸检测算法。对图像做肤色检测,将检测到的区域进行形态学处理,并作为感兴趣区域,完成AdaBoost人脸检测,以得到检测结果。实验结果表明,该算法在嵌入式系统上运行稳定,能提高检测速度和检测正确率。
关键词:
嵌入式系统,
视频人脸检测,
肤色检测,
感兴趣区域,
AdaBoost算法,
形态学处理
Abstract: An improved face detection algorithm is proposed to solve the problem of slow speed in real-time HD video face detection. This paper does face detection on high color image, gets the morphology processing detection results, sets the Region of Interest(ROI), and does AdaBoost face detection on ROI to get the result. Experimental results show that the algorithm can steadily operate on embedded systems, and improve the detection accuracy and the detection speed.
Key words:
embedded system,
video face detection,
skin color detection,
Region of Interest(ROI),
AdaBoost algorithm,
morphology processing
中图分类号:
李明瑞, 傅明, 曹敦. 基于肤色检测的AdaBoost人脸检测算法改进[J]. 计算机工程, 2012, 38(19): 147-150.
LI Meng-Rui, FU Meng, CAO Dui. Improvement of AdaBoost Face Detection Algorithm Based on Skin Color Detection[J]. Computer Engineering, 2012, 38(19): 147-150.