Convexity Grouping of Salient Contours

Corcoran, Padraig; Mooney, Peter; Tilton, James C.

doi:10.1007/978-3-642-20844-7_24

Cited by 4 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to closure, there are a number of other global shape attributes known to be perceptually important that might play a role in perceptual grouping. These include convexity (Jacobs, 1996;Liu, Jacobs, & Basri, 1999;Corcoran, Mooney, & Tilton, 2011) and symmetry and parallelism (Lowe, 1985;Mohan & Nevatia, 1992;Wagemans, 1995;Zisserman et al, 1995;Jepson, Richards, & Knill, 1996;Behrmann, Zemel, & Mozer, 1998;Jacobs, 2003;Feldman, 2007;Sasaki, 2007;Stahl & Wang, 2008;Machilsen, Pauwels, Wagemans, 2009). Wilder, Feldman, and Singh (2016) have also advanced a more general theory of shape detectability based on efficient coding.…”

Section: Other Global Cuesmentioning

confidence: 99%

The role of global cues in the perceptual grouping of natural shapes

2018

View full text Add to dashboard Cite

Perceptual grouping of the bounding contours of objects is a crucial step in visual scene understanding and object recognition. The standard perceptual model for this task, supported by a convergence of physiological and psychophysical evidence, is based upon an association field that governs local grouping, and a Markov or transitivity assumption that allows global contours to be inferred solely from these local cues. However, computational studies suggest that these local cues may not be sufficient for reliable identification of object boundaries in natural scenes. Here we employ a novel psychophysical method to assess the potential role of more global factors in the perceptual grouping of natural object contours. Observers were asked to detect briefly presented fragmented target contours in oriented element noise. We employed natural animal shape stimuli, which in addition to local grouping cues possess global regularities that could potentially be exploited to guide grouping and thereby improve target detection performance. To isolate the role of these global regularities we contrasted performance with open and closed control target stimuli we call local metamers, as they afford the same local grouping cues as animal shapes. We found that performance for closed metamers exceeded performance for open metamers, while performance for animal targets exceeded both, indicating that global grouping cues represented in higher visual areas codetermine the association between orientation signals coded in early visual cortex. These results demand a revision to the standard model for perceptual grouping of contours to accommodate feedback from higher visual areas coding global shape properties.

show abstract

Section: Other Global Cuesmentioning

confidence: 99%

The role of global cues in the perceptual grouping of natural shapes

2018

View full text Add to dashboard Cite

show abstract

“…This example highlights an inability of the proposed technique in some cases to distinguish object boundaries and strong object texture. This inaccuracy could be introduced by integrating prior knowledge in the form of specific object shape information or more generic rules regarding the shape of genuine object contours [31].…”

Section: Individual Complementary Gradientsmentioning

confidence: 99%

Complementary texture and intensity gradient estimation and fusion for watershed segmentation

Corcoran

Winstanley

Mooney

2010

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

In this paper, we identify two current challenges associated with watershed segmentation algorithms which attempt to fuse the visual cues of texture and intensity. The first challenge is that most existing techniques use a competing gradient set which does not allow boundaries to be defined in terms of both visual cues. The second challenge is that these techniques fail to account for the spatial uncertainty inherent in texture gradients. We present a watershed segmentation algorithm which provides a suitable solution to both these challenges and minimises the spatial uncertainty in boundary localisation. This is achieved by a novel fusion algorithm which uses morphological dilation to integrate intensity and texture gradients. A quantitative and qualitative evaluation of results is provided demonstrating that our algorithm outperforms three existing watershed algorithms.

show abstract

The Oxford Handbook of Perceptual Organization

Wagemans¹

2015

View full text Add to dashboard Cite

Everything that is visible has certain colour-properties" (Katz, 1911, p. 1). In this chapter we first discuss the structure and perceptual dimensions that are inherent to the attribute of colour itself. We then consider the strong organisational influence that colour can have on scenes, before considering the interplay of colour, form, depth and movement, to the extent that these interactions influence our perceptual organisation. We discuss spatial factors as they bear on colour, in classical displays of colour contrast and assimilation and the way in which these are modified by perceptual grouping. Finally we consider a world of illuminated objects, highlighting the spatio-chromatic signatures associated with changes in illumination or spectrally selective filtering, and the subtle chromatic cues to material properties. Colour emerges as a subject of perception, that "draws its beauty from the marvellous cooperation of colour-substance and illumination" (Katz, 1911, p. 2), and as the perceptual correlate of a physical signature that supports our visual appreciation of things made of particular stuff.

show abstract

Convexity Grouping of Salient Contours

Cited by 4 publications

References 16 publications

The role of global cues in the perceptual grouping of natural shapes

The role of global cues in the perceptual grouping of natural shapes

Complementary texture and intensity gradient estimation and fusion for watershed segmentation

The Oxford Handbook of Perceptual Organization

Contact Info

Product

Resources

About