The importance of spatial configuration information for object class recognition is widely recognized. Single isolated local appearance codes are often ambiguous. On the other hand, object classes are often characterized by groups of local features appearing in a specific spatial structure. Learning these structures can provide additional discriminant cues and boost recognition performance. However, the problem of learning such features automatically from raw images remains largely uninvestigated. In contrast to previous approaches which require accurate localization and segmentation of objects to learn spatial information, we propose learning by hierarchical voting to identify frequently occurring spatial relationships among local features directly from raw images. The method is resistant to common geometric perturbations in both the training and test data. We describe a novel representation developed to this end and present experimental results that validate its efficacy by demonstrating the improvement in class recognition results realized by including the additional learned information.
Hierarchical Learning of Dominant Constellations for Object Class Recognition
Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007
01.01.2007
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Local Feature , Visual Word , Constellation Representation , Class Recognition , Vote Space Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence , Biometrics , Algorithm Analysis and Problem Complexity
Pattern Recognition of Star Constellations
Online Contents | 1993
|NTRS | 1985
|Object Class Recognition by Unsupervised Scale-Invariant Learning
British Library Conference Proceedings | 2003
|