Structure Is a Visual Class Invariant

B Xiao, Yi Zhe Song, Anupriya Balikai, P M Hall

Research output: Chapter or section in a book/report/conference proceedingChapter or section

3 Citations (SciVal)


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.
Original languageEnglish
Title of host publicationStructural, Syntactic, and Statistical Pattern Recognition
EditorsN DaVitoria Lobo, T Kasparis, F Roli, J T Kwok, M Georgiopoulos, G C Anagnostopoulos, M Loog
Place of PublicationBerlin
Number of pages10
ISBN (Print)978-3-540-89688-3
Publication statusPublished - 2008
EventJoint International Workshop on Structural, Syntactic, and Statistical Pattern Recognition - Orlando, FL
Duration: 1 Jan 2008 → …

Publication series

NameLecture Notes in Computer Science


ConferenceJoint International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
CityOrlando, FL
Period1/01/08 → …

Bibliographical note

Proceedings of the Joint International Workshop on Structural, Syntactic, and Statistical Pattern Recognition. Univ Central Florida, Orlando, Florida, USA, 4-16 December 2008


Dive into the research topics of 'Structure Is a Visual Class Invariant'. Together they form a unique fingerprint.

Cite this