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 you can define; but the true essence of any man, say, for instance, of Abraham Lincoln, remains the endlessly elusive and mysterious object of the biographer’s interest, of the historian’s comments, of popular legend, and of patriotic devotion.”
—Josiah Royce (1855–1916)
“on the instant clamorous eaves,
A climbing moon upon an empty sky,
And all that lamentation of the leaves,
Could but compose man’s image and his cry.”
—William Butler Yeats (1865–1939)