Ecological statistics of Gestalt laws for the perceptual organization of contours.

By James H. Elder, Richard M. Goldberg. 2002

381 citations recorded by the source corpus.

Although numerous studies have measured the strength of visual grouping cues for controlled psychophysical stimuli, little is known about the statistical utility of these various cues for natural images. In this study, we conducted experiments in which human participants trace perceived contours in natural images. These contours are automatically mapped to sequences of discrete tangent elements detected in the image. By examining relational properties between pairs of successive tangents on these traced curves, and between randomly selected pairs of tangents, we are able to estimate the likelihood distributions required to construct an optimal Bayesian model for contour grouping. We employed this novel methodology to investigate the inferential power of three classical Gestalt cues for contour grouping: proximity, good continuation, and luminance similarity. The study yielded a number of important results: (1) these cues, when appropriately defined, are approximately uncorrelated, suggesting a simple factorial model for statistical inference; (2) moderate image-to-image variation of the statistics indicates the utility of general probabilistic models for perceptual organization; (3) these cues differ greatly in their inferential power, proximity being by far the most powerful; and (4) statistical modeling of the proximity cue indicates a scale-invariant power law in close agreement with prior psychophysics.

Subfields: Atomic and Molecular Physics, and Optics, Cognitive Neuroscience, Computer Vision and Pattern Recognition, Social Psychology, Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Social Psychology

In Cognitive Science & Psychology

Citations in the corpus

Holistically-Nested Edge Detection (2015, background): “…response fusion [38, 30, 28], (3) engagement of different levels of visual perception [16, 25, 37, 15] such as mid-level Gestalt law information [7], (4) structural information [6] and context [36], (5) holistic image prediction [23], (6) 3D geometry [13], and (7) occlusion boundaries [14].”
A coherent computational approach to model bottom-up visual attention (2006, methodology): “Most of the recent computational models are based on the Gestalt principles of colinearity and proximity [ 42 ], [43].”
Object perception as Bayesian inference. (2004, background): “See also Elder and Goldberg (2002).”
Visual perception and the statistical properties of natural scenes. (2008, background): “For example, Elder & Goldberg (1998, 2002) and Geisler et al. (2001, Geisler & Perry 2006) measured the pair-wise statistics of image contours that were hand segmented from natural images.”
Multi-scale Improves Boundary Detection in Natural Images (2008, background): “In particular, scaling phenomena h ave been observed in the statistics of boundary contours [17, 18].”
The Visual System's Internal Model of the World (2015, background): “…hierarchical architecture of the biological visual system and share many fundamental characteristics, they represent different perspectives how the internal model can be learned and used for inference, and in my opinion, each capturing or emphasizing certain elements of the reality of the brain.”
Phase Consistent Ecological Domain Adaptation (2020, background): “For the classifier in the target domain, even in the absence of annotations, a target image informs the set of possible hypotheses (segmentations), due to the statistical regularities of natural scenes (ecological statistics, [3, 11]).”
A Century of Gestalt Psychology in Visual Perception II. Conceptual and Theoretical Foundations (2012, positive): “The connection between the statistical structure of contours and the empirical statistics of naturally occurring object boundaries has been made more explicit by Elder and Goldberg (2002) and by Geisler, Perry, Super, and Gallogly (2001).”
A systematic comparison between visual cues for boundary detection. (2016, methodology): “Direct measurements of ground-truth information for the location of physical boundaries would be extremely challenging in natural scenes; hence a common shortcut is to rely on manual segmentation by human observers (Geisler et al., 2001; Elder & Goldberg, 2002; Martin et al., 2004).”
Bayesian models of object perception. (2003, methodology): “Statistics on the geometry of contours have been used to explain aspects of human perception [18 ,19 ], and statistical shape regularities enable computer vision systems to group image features consistent with the constraints identified by Gestalt psychologists, such as requiring that nearby edges w”
Space and time in visual context (2007, background): “Although the full distribution over natural movies P ( I ) eludes exact description, it is known that most objects in the visual world have large spatial and temporal footprint”
An overview of quantitative approaches in Gestalt perception. (2016, positive): “In fact, in the case of good continuation one can justify the assumptions that are built into the priors by looking at the statistics of edges and contours in ‘‘the real world” (Brunswik & Kamiya, 2001; Geisler, Perry, Super, & Gallogly, 2001; Elder & Goldberg, 2002).”
Edge and line oriented contour detection: State of the art (2011, background): “Edge pixels can be grouped together into contours, according to the Gestalt laws of proximity, good continuation and, more recently, closure [157] (Fig.”
A Century of Gestalt Psychology in Visual Perception I. Perceptual Grouping and Figure-Ground Organization (2012, background): “Elder and Goldberg (2002) estimated these distributions more directly, asking human observers to label the sequence of elements forming the contours of natural images, with the aid of an interactive image editing tool.”