识别，基于内容的检索，检测

It is important to understand the distinction of visual categorization from three related problems:
Recognition: This concerns the identification of particular object instances. For instance, recognition would distinguish between images of two structurally distinct

cups, while categorization would place them in the same class.

识别：特定对象实例的确定。比如，识别会区分两类结构不同的杯子的图像。

Content Based Image Retrieval: This refers to the process of retrieving images on the basis of low-level image features, given a query image or manually constructed description of these low-level features. Such descriptions frequently have little relation to the semantic content of the image.

基于内容的图像检索：基于低层的图像特征检索图像
Detection: This refers to deciding whether or not a member of one visual category is present in a given image. Most previous work on detection has centered on machine learning approaches to detecting faces, cars or pedestrians [1]-[6] While it would be possible to perform generic categorization by applying a detector for each class of interest to a given image, this approach becomes inefficient given a large number of classes. In contrast to the technique proposed in this paper, most existing detection techniques require precise manual alignment of the training images and the segregation of these images into different views [5], neither of which is necessary in our approach
检测：检测一个感兴趣的视觉类别是否出现在图像中。可以用一般化视觉分类的检测器检查感兴趣的类别，但是当类别数量增多时，效率降低。与分类比，现在的大多检测技术需要精确的手动对齐训练图像和将图像分到不同视角？

参考文献;Visual Categorization with Bags of Keypoints