In computer vision, the problem of object categorization from image search is the problem of training a classifier to recognize categories of objects, using only the images retrieved automatically with an Internet search engine. Ideally, automatic image collection would allow classifiers to be trained with nothing but the category names as input. This problem is closely related to that of content-based image retrieval (CBIR), where the goal is to return better image search results rather than training a classifier for image recognition.
Traditionally, classifiers are trained using sets of images that are labeled by hand. Collecting such a set of images is often a very time-consuming and laborious process. The use of Internet search engines to automate the process of acquiring large sets of labeled images has been described as a potential way of greatly facilitating computer vision research.
Read more about Object Categorization From Image Search: PLSA Approach, OPTIMOL, Object Categorization in Content-based Image Retrieval
Famous quotes containing the words object, image and/or search:
“The sick man is taken away by the institution that takes charge not of the individual, but of his illness, an isolated object transformed or eliminated by technicians devoted to the defense of health the way others are attached to the defense of law and order or tidiness.”
—Michel de Certeau (1925–1986)
“That myth—that image of the madonna-mother—has disabled us from knowing that, just as men are more than fathers, women are more than mothers. It has kept us from hearing their voices when they try to tell us their aspirations . . . kept us from believing that they share with men the desire for achievement, mastery, competence—the desire to do something for themselves.”
—Lillian Breslow Rubin (20th century)
“I never found even in my juvenile hours that it was necessary to go a thousand miles in search of themes for moralizing.”
—Horace Walpole (1717–1797)