Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2007-12-02
Computer Science
Computer Vision and Pattern Recognition
Scientific paper
Learning object models from views in 3D visual object recognition is usually formulated either as a function approximation problem of a function describing the view-manifold of an object, or as that of learning a class-conditional density. This paper describes an alternative framework for learning in visual object recognition, that of learning the view-generalization function. Using the view-generalization function, an observer can perform Bayes-optimal 3D object recognition given one or more 2D training views directly, without the need for a separate model acquisition step. The paper shows that view generalization functions can be computationally practical by restating two widely-used methods, the eigenspace and linear combination of views approaches, in a view generalization framework. The paper relates the approach to recent methods for object recognition based on non-uniform blurring. The paper presents results both on simulated 3D ``paperclip'' objects and real-world images from the COIL-100 database showing that useful view-generalization functions can be realistically be learned from a comparatively small number of training examples.
No associations
LandOfFree
Learning View Generalization Functions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Learning View Generalization Functions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning View Generalization Functions will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-469403