Sparse feature maps in a scale hierarchy
2000 (English)In: Algebraic Frames for the Perception-Action Cycle, Proceedings Second International Workshop, AFPAC 2000 / [ed] Gerald Sommer and Yehoshua Y. Zeevi, Berlin, Heidelberg: Springer Berlin/Heidelberg, 2000, Vol. 1888, 186-196 p.Conference paper (Refereed)
This article describes an essential step towards what is called a view centered representation of the low-level structure in an image. Instead of representing low-level structure (lines and edges) in one compact feature map, we will separate structural information into several feature maps, each signifying features at a characteristic phase, in a specific scale. By characteristic phase we mean the phases 0, pi, and +/-pi/2, corresponding to bright, and dark lines, and edges between different intensity levels, or colours. A lateral inhibition mechanism selects the strongest feature within each local region of scale represented. The scale representation is limited to maps one octave apart, but can be interpolated to provide a continous representation. The resultant image representation is sparse, and thus well suited for further processing, such as pattern detection.
Place, publisher, year, edition, pages
Berlin, Heidelberg: Springer Berlin/Heidelberg, 2000. Vol. 1888, 186-196 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 1888
sparse coding, image representation, view centered representation, edge detection, scale hierarchy, characteristic phase
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-48937DOI: 10.1007/10722492_13ISBN: 978-3-540-41013-3 (print)ISBN: 978-3-540-45260-7 (online)OAI: oai:DiVA.org:liu-48937DiVA: diva2:269833
AFPAC 2000: Second International Workshop for Algebraic Frames for the Perception-Action Cycle, 10-11 September 2000, Kiel, Germany