Change search
ReferencesLink to record
Permanent link

Direct link
Class-specific material categorisation
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2005 (English)In: TENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1 AND 2, PROCEEDINGS, 2005, 1597-1604 p.Conference paper (Refereed)
Abstract [en]

Although a considerable amount of work has been published on material classification, relatively little of it studies situations with considerable variation within each class. Many experiments use the exact same sample, or different patches front the same image, for training and test sets. Thus, such studies are vulnerable to effectively recognising one particular sample of a material as opposed to the material category. In contrast, this paper places firm emphasis on the capability to generalise to previously, unseen instances of materials. We adopt an appearance-based strategy, and conduct experiments on a new database which contains several samples of each of eleven material categories, imaged under a variety of pose, illumination and scale conditions. Together these sources of intra-class variation provide a stern challenge indeed for recognition. Somewhat surprisingly, the difference in performance between various state-of-the-art texture descriptors proves rather small in this task. On the other hand, we clearly demonstrate that very significant gains can be achieved via different SVM-based classification techniques. Selecting appropriate kernel parameters proves crucial. This motivates a novel recognition scheme based on a decision tree. Each node contains an SVM to split one class front all others with a kernel parameter optimal for that particular node. Hence, each decision is made using a different, optimal., class-specific metric. Experiments show the superiority of this approach over several state-of-the-art classifiers.

Place, publisher, year, edition, pages
2005. 1597-1604 p.
, IEEE International Conference on Computer Vision, ISSN 1550-5499
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-42803DOI: 10.1109/ICCV.2005.54ISI: 000233155100209ScopusID: 2-s2.0-33745899935ISBN: 0-7695-2334-XOAI: diva2:447597
10th IEEE International Conference on Computer Vision (ICCV 2005) Location: Beijing, PEOPLES R CHINA Date: OCT 17-20, 2005
QC 20111012Available from: 2011-10-12 Created: 2011-10-12 Last updated: 2011-10-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Caputo, BarbaraHayman, Eric
By organisation
Computer Vision and Active Perception, CVAP
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
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

Altmetric score

Total: 15 hits
ReferencesLink to record
Permanent link

Direct link