Basic image features (BIFs) arising from approximate symmetry type
| Autor: | Griffin, L.D., Lillholm, M., Crosier, M., Sande, Van, J., Tai, Xue-Cheng, Mørken, K., Lysaker, M., Lie, K.A. |
|---|---|
| Přispěvatelé: | Biomedical Engineering |
| Jazyk: | angličtina |
| Rok vydání: | 2009 |
| Předmět: |
business.industry
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Filter (signal processing) Image (mathematics) Image texture Local symmetry Computer Science::Computer Vision and Pattern Recognition Artificial intelligence Symmetry (geometry) business Group theory Linear filter Feature detection (computer vision) Mathematics |
| Zdroj: | Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2009) 1-5 June 2009, Voss, Norway, 343-355 STARTPAGE=343;ENDPAGE=355;TITLE=Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2009) 1-5 June 2009, Voss, Norway Lecture Notes in Computer Science ISBN: 9783642022555 SSVM |
| Popis: | We consider detection of local image symmetry using linear filters. We prove a simple criterion for determining if a filter is sensitive to a group of symmetries. We show that derivative-of-Gaussian (DtG) filters are excellent at detecting local image symmetry. Building on this, we propose a very simple algorithm that, based on the responses of a bank of six DtG filters, classifies each location of an image into one of seven Basic Image Features (BIFs). This effectively and efficiently realizes Marr's proposal for an image primal sketch. We summarize results on the use of BIFs for texture classification, object category detection, and pixel classification. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|