A Tangent Bundle Theory for Visual Curve Completion
- PMID: 22201060
- DOI: 10.1109/TPAMI.2011.262
A Tangent Bundle Theory for Visual Curve Completion
Abstract
Visual curve completion is a fundamental perceptual mechanism that completes the missing parts (e.g., due to occlusion) between observed contour fragments. Previous research into the shape of completed curves has generally followed an "axiomatic" approach, where desired perceptual/geometrical properties are first defined as axioms, followed by mathematical investigation into curves that satisfy them. However, determining psychophysically such desired properties is difficult and researchers still debate what they should be in the first place. Instead, here we exploit the observation that curve completion is an early visual process to formalize the problem in the unit tangent bundle R(2) × S(1), which abstracts the primary visual cortex (V1) and facilitates exploration of basic principles from which perceptual properties are later derived rather than imposed. Exploring here the elementary principle of least action in V1, we show how the problem becomes one of finding minimum-length admissible curves in R(2) × S(1). We formalize the problem in variational terms, we analyze it theoretically, and we formulate practical algorithms for the reconstruction of these completed curves. We then explore their induced visual properties vis-à-vis popular perceptual axioms and show how our theory predicts many perceptual properties reported in the corresponding perceptual literature. Finally, we demonstrate a variety of curve completions and report comparisons to psychophysical data and other completion models.
Similar articles
-
Tangent Bundle Elastica and Computer Vision.IEEE Trans Pattern Anal Mach Intell. 2015 Jan;37(1):161-74. doi: 10.1109/TPAMI.2014.2343214. IEEE Trans Pattern Anal Mach Intell. 2015. PMID: 26353216
-
Tangent bundle curve completion with locally connected parallel networks.Neural Comput. 2012 Dec;24(12):3277-316. doi: 10.1162/NECO_a_00365. Epub 2012 Sep 12. Neural Comput. 2012. PMID: 22970873
-
Confuse your illusion: feedback to early visual cortex contributes to perceptual completion.Psychol Sci. 2013 Jan 1;24(1):63-71. doi: 10.1177/0956797612449175. Epub 2012 Dec 10. Psychol Sci. 2013. PMID: 23228938
-
Neural basis of shape representation in the primate brain.Prog Brain Res. 2006;154:293-313. doi: 10.1016/S0079-6123(06)54016-6. Prog Brain Res. 2006. PMID: 17010719 Review.
-
The neurogeometry of pinwheels as a sub-Riemannian contact structure.J Physiol Paris. 2003 Mar-May;97(2-3):265-309. doi: 10.1016/j.jphysparis.2003.10.010. J Physiol Paris. 2003. PMID: 14766146 Review.
Cited by
-
Reconnection of Interrupted Curvilinear Structures via Cortically Inspired Completion for Ophthalmologic Images.IEEE Trans Biomed Eng. 2018 May;65(5):1151-1165. doi: 10.1109/TBME.2017.2787025. IEEE Trans Biomed Eng. 2018. PMID: 29683430 Free PMC article.
-
Typical curve with G1 constraints for curve completion.Vis Comput Ind Biomed Art. 2021 Nov 26;4(1):28. doi: 10.1186/s42492-021-00095-9. Vis Comput Ind Biomed Art. 2021. PMID: 34825266 Free PMC article.
-
Shape recognition: convexities, concavities and things in between.Sci Rep. 2015 Nov 24;5:17142. doi: 10.1038/srep17142. Sci Rep. 2015. PMID: 26598139 Free PMC article.
-
Spatially-global integration of closed, fragmented contours by finding the shortest-path in a log-polar representation.Vision Res. 2016 Sep;126:143-163. doi: 10.1016/j.visres.2015.06.007. Epub 2015 Aug 14. Vision Res. 2016. PMID: 26241462 Free PMC article.
-
Combining contour and region for closed boundary extraction of a shape.Front Psychol. 2023 Nov 15;14:1198691. doi: 10.3389/fpsyg.2023.1198691. eCollection 2023. Front Psychol. 2023. PMID: 38034308 Free PMC article.
Publication types
LinkOut - more resources
Full Text Sources