Unsupervised Visual Object Class Recognition
Athanasios K. Noulas, Ben Kröse · 2006
Object class recognition is a very well studied problem in the domain of Computer Vision. Lately, the most successful approaches extract informative descriptors from the images, organize them and use machine learning techniques for learning and classification tasks. A common approach involves the construction of a visual vocabulary which is used to express the content of the image, and the application of text retrieval techniques for inference purposes. In this paper we present an unsupervised implementation of this approach. 1