Structure Is a Visual Class Invariant
Xiao, B., Song, Y. Z., Balikai, A. and Hall, P. M., 2008. Structure Is a Visual Class Invariant. In: DaVitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J. T., Georgiopoulos, M., Anagnostopoulos, G. C. and Loog, M., eds. Structural, Syntactic, and Statistical Pattern Recognition. Vol. 5342/2008. 5342/2008 ed. Berlin: Springer, pp. 329-338. (Lecture Notes in Computer Science)
Related documents:This repository does not currently have the full-text of this item.
You may be able to access a copy if URLs are provided below.
The problem of learning the class identity of visual objects has received considerable attention recently. With rare exception, all of the work to date assumes low variation in appearance, which limits them to a single depictive style usually photographic. The same object depicted in other styles - as a drawing, perhaps - cannot be identified reliably. Yet humans are able to name the object no matter how it is depicted, and even recognise a real object having previously seen only a drawing. This paper describes a classifier which is unique in being able to learn class identity no matter how the class instances are depicted. The key to this is our proposition that topological structure is a class invariant. Practically, we depend on spectral graph analysis of a hierarchical description of an image to construct a feature vector of fixed dimension. Hence structure is transformed to a feature vector, which can be classified using standard methods. We demonstrate the classifier on several diverse classes.
|Item Type||Book Sections|
|Creators||Xiao, B., Song, Y. Z., Balikai, A. and Hall, P. M.|
|Editors||DaVitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J. T., Georgiopoulos, M., Anagnostopoulos, G. C. and Loog, M.|
|Departments||Faculty of Science > Computer Science|
|Additional Information||Proceedings of the Joint International Workshop on Structural, Syntactic, and Statistical Pattern Recognition. Univ Central Florida, Orlando, Florida, USA, 4-16 December 2008|
Actions (login required)