欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了提高人脸检测的速度,提出了一种基于特征和基于图像相结合的快速人脸检测方法。该方法对训练样本图像进行离散小波变换（DWT）,使用低频逼近系数来训练支持向量机（SVM）分类器;在检测时,首先利用双眼区域的亮度关系和脸部的对称特征来快速过滤掉大量的背景区域,再利用SVM对余下的区域进行进一步的验证,以确认是否为人脸。实验结果证明了该方法的正确性和有效性。
英文摘要：
In order to improve the speed of detecting human face, an algorithm of fast face detection method combining both feature-based and image-based was presented. In the training step, the smooth approximation coefficients getted by wavelet transform were used for training the SVM, in the detection step, firstly, the characteristics of intensity in eye region and symmetry in face were used for finding face candidates, and all the candidates were verified by SVM. Experimental results show that the new algorithm is feasible and efficient.
同期刊论文项目
同项目期刊论文
期刊信息
位置：