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:
“Man is to himself the most wonderful object in nature; for he cannot conceive what the body is, still less what the mind is, and least of all how a body should be united to a mind. This is the consummation of his difficulties, and yet this is his very being.”
—Blaise Pascal (1623–1662)
“You make yourselves out to be shepherds of the flock and yet you allow your sheep to live in filth and poverty. And if they try and raise their voices against it, you calm them by telling them their suffering is the will of God. Sheep, indeed. Are we sheep to be herded and sheared by a handful of owners? I was taught man was made in the image of God, not a sheep.”
—Philip Dunne (1908–1992)