第九章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 vision to the image retrieval problem, that is, the problem of searching for digital images in large databases. [1].Query by Image and Video Content: The QBIC System, (Flickner, 1995) Content-based means that the search will analyze the actual contents of the image. The term content in this context might refer to colors, shapes, textures, or any other information that can be derived from the image itself. [2].Wikipedia of Content-based Image Retrieval “Content-based” Context Content-based Image Retrieval (CBIR) Object Classification Semantic Gap Red Flower R 239 G 71 B 69 Semantic Gap Human: based on the meaning of objects Computer: based on the metadata Data driven Model based [4] L.-J. Li, R. Socher, and L. Fei-Fei. Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In CVPR 2009. [3] Xin-Jing Wang, Lei Zhang, Ming Liu, Yi Li, Wei-Ying Ma. ARISTA - Image Search to Annotation on Billions of Web Photos. In CVPR 2010. Data driven Model based Object Bag of ‘words’ Analogy to documents Of all the sensory impressions proceeding to the brain, the visual experiences are the dominant ones. Our perception of the world around us is based essentially on the messages that reach the brain from our eyes. For a long time it was thought that the retinal image was transmitted point by point to visual centers in the brain; the