Concepts of rectangle features and "integral image" are introduced. And based on the basic principle of Adaboost algorithm and rectangle features, the cascade classfiers for face detection and eyes location is constructed.
3.介绍了矩形特征和积分图像的概念,研究了Adaboost机器学习算法的基本原理,应用Adaboost算法和矩形特征构建了人脸检测和眼睛检测层叠分类器,实现了人脸和眼睛的实时检测,并测试了分类器的性能。
参考来源 - 基于人脸识别的身份查询原型系统的设计与开发Based on previous research,the structures of Haar-like rectangular features and integral image that can be used to compute the value of features rapidly are analyzed.
在已有研究的基础上,分析了Haar-like矩形特征的组成形式以及利用积分图像法快速计算矩形特征的方法。
参考来源 - 基于Haar·2,447,543篇论文数据,部分数据来源于NoteExpress
实现了一种基于矩形特征的人脸检测算法。
A face detection algorithm is implemented based on rectangle features.
矩形特征模板的卷积可以用积分图进行快速计算,该方法使特征检测的速度得到了很大提高。
Then, integral image is used to rapidly calculate the convolution of rectangular feature templates, so the detection of scale-space geometric features is greatly accelerated in the method.
结果表明:循环伏安曲线为矩形特征,炭黑电极表现出典型的电容行为,扫描速度与比电容基本无关;
It was showed that the rectangular CV curves and linear potential-time curves exhibited typical capacitive behavior of CB electrode.
应用推荐