Object Categorization in Content-based Image Retrieval
Typically, image searches only make use of text associated with images. The problem of content-based image retrieval is that of improving search results by taking into account visual information contained in the images themselves. Several CBIR methods make use of classifiers trained on image search results, to refine the search. In other words, object categorization from image search is one component of the system. OPTIMOL, for example, uses a classifier trained on images collected during previous iterations to select additional images for the returned dataset.
Examples of CBIR methods that model object categories from image search are:
- Fergus et al., 2004
- Berg and Forsyth, 2006
- Yanai and Barnard, 2006
Read more about this topic: Object Categorization From Image Search
Famous quotes containing the words object and/or image:
“Did men but consider that the sun, moon, and stars, and every other object of the senses, are only so many sensations in their minds, which have no other existence but barely being perceived, doubtless they would never fall down and worship their own ideas; but rather address their homage to that eternal invisible Mind which produces and sustains all things.”
—George Berkeley (1685–1753)
“Not for nothing does it say in the Commandments ‘Thou shalt not make unto thee any image’ ... Every image is a sin.... When you love someone you leave every possibility open to them, and in spite of all the memories of the past you are ready to be surprised, again and again surprised, at how different they are, how various, not a finished image.”
—Max Frisch (1911–1991)