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:
“Our systems, perhaps, are nothing more than an unconscious apology for our faults—a gigantic scaffolding whose object is to hide from us our favorite sin.”
—Henri-Frédéric Amiel (1821–1881)
“Our ego ideal is precious to us because it repairs a loss of our earlier childhood, the loss of our image of self as perfect and whole, the loss of a major portion of our infantile, limitless, ain’t-I-wonderful narcissism which we had to give up in the face of compelling reality. Modified and reshaped into ethical goals and moral standards and a vision of what at our finest we might be, our dream of perfection lives on—our lost narcissism lives on—in our ego ideal.”
—Judith Viorst (20th century)