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 aim of science is to apprehend this purely intelligible world as a thing in itself, an object which is what it is independently of all thinking, and thus antithetical to the sensible world.... The world of thought is the universal, the timeless and spaceless, the absolutely necessary, whereas the world of sense is the contingent, the changing and moving appearance which somehow indicates or symbolizes it.”
—R.G. (Robin George)
“For through the painter must you see his skill,
To find where your true image pictured lies,
Which in my bosom’s shop is hanging still,”
—William Shakespeare (1564–1616)
“When you start with a portrait and search for a pure form, a clear volume, through successive eliminations, you arrive inevitably at the egg. Likewise, starting with the egg and following the same process in reverse, one finishes with the portrait.”
—Pablo Picasso (1881–1973)