Literature DB >> 22201060

A Tangent Bundle Theory for Visual Curve Completion.

Guy Ben-Yosef1, Ohad Ben-Shahar.   

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.

Entities:  

Year:  2011        PMID: 22201060     DOI: 10.1109/TPAMI.2011.262

Source DB:  PubMed          Journal:  IEEE Trans Pattern Anal Mach Intell        ISSN: 0098-5589            Impact factor:   6.226


  5 in total

1.  Reconnection of Interrupted Curvilinear Structures via Cortically Inspired Completion for Ophthalmologic Images.

Authors:  Jiong Zhang; Erik Bekkers; Da Chen; Tos T J M Berendschot; Jan Schouten; Josien P W Pluim; Yonggang Shi; Behdad Dashtbozorg; Bart M Ter Haar Romeny
Journal:  IEEE Trans Biomed Eng       Date:  2018-05       Impact factor: 4.538

2.  Bayesian hierarchical grouping: Perceptual grouping as mixture estimation.

Authors:  Vicky Froyen; Jacob Feldman; Manish Singh
Journal:  Psychol Rev       Date:  2015-08-31       Impact factor: 8.934

3.  Association Fields via Cuspless Sub-Riemannian Geodesics in SE(2).

Authors:  R Duits; U Boscain; F Rossi; Y Sachkov
Journal:  J Math Imaging Vis       Date:  2014       Impact factor: 1.627

4.  Spatially-global integration of closed, fragmented contours by finding the shortest-path in a log-polar representation.

Authors:  TaeKyu Kwon; Kunal Agrawal; Yunfeng Li; Zygmunt Pizlo
Journal:  Vision Res       Date:  2015-08-14       Impact factor: 1.886

5.  Shape recognition: convexities, concavities and things in between.

Authors:  Gunnar Schmidtmann; Ben J Jennings; Frederick A A Kingdom
Journal:  Sci Rep       Date:  2015-11-24       Impact factor: 4.379

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.