Change search
ReferencesLink to record
Permanent link

Direct link
A new kernel method for object recognition:spin glass-Markov random fields
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
2004 (English)Doctoral thesis, monograph (Other scientific)
Abstract [en]

Recognizing objects through vision is an important part of our lives: we recognize people when we talk to them, we recognize our cup on the breakfast table, our car in a parking lot, and so on. While this task is performed with great accuracy and apparently little effort by humans, it is still unclear how this performance is achieved. Creating computer methods for automatic object recognition gives rise to challenging theoretical problems such as how to model the visual appearance of the objects or categories we want to recognize, so that the resulting algorithm will perform robustly in realistic scenarios; to this end, how to use effectively multiple cues (such as shape, color, textural properties and many others), so that the algorithm uses uses the best subset of cues in the most effective manner; how to use specific features and/or specific strategies for different classes.

The present work is devoted to the above issues. We propose to model the visual appearance of objects and visual categories via probability density functions. The model is developed on the basis of concepts and results obtained in three different research areas: computer vision, machine learning and statistical physics of spin glasses. It consists of a fully connected Markov random field with energy function derived from results of statistical physics of spin glasses. Markov random fields and spin glass energy functions are combined together via nonlinear kernel functions; we call the model Spin Glass-Markov Random Fields. Full connectivity enables to take into account the global appearance of the object, and its specific local characteristics at the same time, resulting in robustness to noise, occlusions and cluttered background. Because of properties of some classes of spin glasslike energy functions, our model allows to use easily and effectively multiple cues, and to employ class specific strategies. We show with theoretical analysis and experiments that this new model is competitive with state-of-the-art algorithms for object recognition.

Place, publisher, year, edition, pages
Stockholm: Numerisk analys och datalogi , 2004. , x, 168 p.
Trita-NA, ISSN 0348-2952 ; 0430
Keyword [en]
Keyword [sv]
National Category
Computer Science
URN: urn:nbn:se:kth:diva-58ISBN: 91-7283-896-5OAI: diva2:14490
Public defence
2004-11-26, Sal F2, Lindstedsvägen 28, Stockholm, 14:15
Available from: 2004-10-11 Created: 2004-10-11 Last updated: 2012-03-19Bibliographically approved

Open Access in DiVA

fulltext(2247 kB)609 downloads
File information
File name FULLTEXT01.pdfFile size 2247 kBChecksum SHA-1
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Caputo, Barbara
By organisation
Numerical Analysis and Computer Science, NADA
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 609 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 877 hits
ReferencesLink to record
Permanent link

Direct link