第九章 和人脸检测与图像检索.pptVIP

* 分级分类器的构建 采用由粗到细的思想（coarse to fine） 将少量区分性好的特征构成的简单分类器置于前面若干层 效果：放过检测绝大多数人脸的同时，排除大量非脸 后面层包含更多次重要的特征对非脸进行进一步排除 训练方法关键思路 每层训练用非脸样本使用前面层分类器误判为人脸的那些样本 * 检测过程流程图 AdaBoost Learner Feature set Feature Select Classifier Stage 1 False (Reject) AdaBoost Learner Stage 2 Pass False (Reject) AdaBoost Learner Stage 3 Pass False (Reject) Reject as many negatives as possible ? (minimize the false negative) 100% Detection Rate 50% False Positive * 一些检测结果 Content-based Image Retrieval(CBIR) Content-based image retrieval (CBIR), also known as query by image content (QBIC) , is the application of computer