Content Based Image Retrieval

Under Content Based Image Retrieval ( CBIR ) refers to a content-based image search. Alternative names are query by image content ( QBIC ) and content-based visual information retrieval ( CBVIR ). It is a specialized field of image processing and retrieval of information ( information retrieval ) in large databases (see for an overview ).

" Content based " (content based) here means an analysis of the current contents of an image, so the colors, contours, surfaces ( textures) or other information (so-called feature vectors ), which can be determined with an automatic image processing. (see also for an introduction ) The task of image search is a list of existing images to sort so that the searched images are as far forward ( as based on a reference image). Images are sorted according to their similarity to the reference image, which is determined by a distance function and the feature vectors of images. A quality measure assesses the sort that is largely dependent on the choice of feature vectors, and the similarity measure.

In contrast to content-based search which is " keyword- based" or " text-based " image search, in which a description of the image is (eg what people are visible, which object is shown or the coordinates of the images ) (see Information Retrieval ).

The content-based image search is applied to images databases in the field of medical image processing and in the search for plagiarism (Near Duplicate Detection ).