In the final , the thesis build a rapid face detection system using a cascaded classifiers based on adaboost learning algorithm , harr - like feature and the method of building classifier 最后本文运用基于adaboost学习算法和harr - like特征及本文提出的由特征构造分类器方法,采用一种分级分类器的结构,搭建了一个快速的人脸检测系统。
Experimental results show that i - casda obtains better results than n . otsu and casda , consuming time less than 0 . 01 second . in the module of character recognition , based on the step of feature extracting cascading classifier - based and svm - based character recognition methods are proposed 实验结果表明,应用该算法对一幅牌照图象进行二值化处理,消耗时间在0 . 01秒以下,优于n . otsu算法和casda算法。
Thirdly , concerning the rotation and the shear of portrait images , the face area can be detected accurately and rapidly by an effective algorithm of the cascade classifier based on adaboost learning method . so the adjustment of zoom is realized . and then , the normal shear is achieved ground on the projection method 第三,针对实现图像的缩放和裁切,采用基于adaboost学习的层叠分类器的人脸检测方法快速准确地检测出人脸区域,利用人脸区域的大小缩放图像;并基于投影的方法实现图像的标准裁切。