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.
|Title of host publication||Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2009) 1-5 June 2009, Voss, Norway|
|Editors||Xue-Cheng Tai, K. Mørken, M. Lysaker, K.A. Lie|
|Place of Publication||Berlin|
|Publication status||Published - 2009|
|Name||Lecture Notes in Computer Science|
Griffin, L. D., Lillholm, M., Crosier, M., & Sande, Van, J. (2009). Basic image features (BIFs) arising from approximate symmetry type. In X-C. Tai, K. Mørken, M. Lysaker, & K. A. Lie (Eds.), Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2009) 1-5 June 2009, Voss, Norway (pp. 343-355). (Lecture Notes in Computer Science; Vol. 5567). Berlin: Springer. https://doi.org/10.1007/978-3-642-02256-2_29