Problem of Object Categorization
Object categorization is a typical task of computer vision which involves determining whether or not an image contains some specific category of object. The idea is closely related with recognition, identification, and detection. Appearance based object categorization typically contains feature extraction, learning a classifier, and applying the classifier to new examples. There are many ways to represent a category of objects, e.g. from shape analysis, bag of words models, or local descriptors such as SIFT, etc. Examples of supervised classifiers are Naive Bayes classifier, SVM, mixtures of Gaussians, neural network, etc. However, recent research has shown that object categories and their locations in images can be discovered in an unsupervised manner as well.
Read more about this topic: Boosting Methods For Object Categorization
Famous quotes containing the words problem of, problem and/or object:
“[How] the young . . . can grow from the primitive to the civilized, from emotional anarchy to the disciplined freedom of maturity without losing the joy of spontaneity and the peace of self-honesty is a problem of education that no school and no culture have ever solved.”
—Leontine Young (20th century)
“If a problem is insoluble, it is Necessity. Leave it alone.”
—Mason Cooley (b. 1927)
“If we cannot accept the importance of the world, which considers itself important, if in the midst of that world our laughter finds no echo, we have but one choice: to take the world as a whole and make it the object of our game; to turn it into a toy.”
—Milan Kundera (b. 1929)