Medial axis generation in a model of perceptual organization

Ardila, Diego; Mihalaş, Ştefan; Heydt, Rüdiger von der; Niebur, Ernst

doi:10.1109/ciss.2012.6310946

Cited by 10 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the response profile of G-cells within a shape corresponds to the points of the shape's skeleton (Craft et al, 2007), as would be expected if they implement a skeletal computation. Indeed, pruned shape skeletons, resembling those extracted from 2D shapes by human participants , can be generated using a model of perceptual organization that incorporates the response profile of G-cells (Ardila et al, 2012).…”

Section: Discussionmentioning

confidence: 99%

“…One way in which to address whether shape skeletons are implicated in both perceptual organization and object recognition would be to test whether regions of the brain involved in these processes also represent the shape skeleton. If shape skeletons are used to create shape percepts, then they should be represented in areas V2, V3, and/or V4 (Ardila, Mihalas, von der Heydt, & Niebur, 2012;von der Heydt, 2015). These regions have been consistently implicated in various aspects of perceptual organization, from determining border ownership of shape contours in V2 (Zhou, Friedman, & von der Heydt, 2000) to resolving shape from motion or illusory contours in V3 and V4 (Caplovitz & Peter, 2010;Mannion, McDonald, & Clifford, 2010).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A dual role for shape skeletons in human vision: perceptual organization and object recognition

Ayzenberg

Kamps

Dilks

et al. 2019

Preprint

View full text Add to dashboard Cite

Shape perception is crucial for object recognition. However, it remains unknown exactly how shape information is represented, and, consequently, used by the visual system. Here, we hypothesized that the visual system incorporates "shape skeletons" to both (1) perceptually organize contours and component parts into a shape percept, and (2) compare shapes to recognize objects. Using functional magnetic resonance imaging (fMRI) and representational similarity analysis (RSA), we found that a model of skeletal similarity explained significant unique variance in the response profiles of V3 and LO, regions known to be involved in perceptual organization and object recognition, respectively. Moreover, the skeletal model remained predictive in these regions even when controlling for other models of visual similarity that approximate low-to high-level visual features (i.e., Gabor-jet, GIST, HMAX, and AlexNet), and across different surface forms, a manipulation that altered object contours while preserving the underlying skeleton. Together, these findings shed light on the functional roles of shape skeletons in human vision, as well as the computational properties of V3 and LO.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A dual role for shape skeletons in human vision: perceptual organization and object recognition

Ayzenberg

Kamps

Dilks

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…These receptive fields bias the grouping cell activity, and consequently salient locations, to fall on the centroids and the medial axis of the proto-objects [Ardila, Mihalas, von der Heydt, and Niebur, 2012]. An example of this is shown in figure 6(a-ii) where the highest activation in the saliency map corresponds to the center of the bar.…”

Section: Discussionmentioning

confidence: 99%

A model of proto-object based saliency

et al. 2014

Self Cite

View full text Add to dashboard Cite

Organisms use the process of selective attention to optimally allocate their computational resources to the instantaneously most relevant subsets of a visual scene, ensuring that they can parse the scene in real time. Many models of bottom-up attentional selection assume that elementary image features, like intensity, color and orientation, attract attention. Gestalt psychologists, how-ever, argue that humans perceive whole objects before they analyze individual features. This is supported by recent psychophysical studies that show that objects predict eye-fixations better than features. In this report we present a neurally inspired algorithm of object based, bottom-up attention. The model rivals the performance of state of the art non-biologically plausible feature based algorithms (and outperforms biologically plausible feature based algorithms) in its ability to predict perceptual saliency (eye fixations and subjective interest points) in natural scenes. The model achieves this by computing saliency as a function of proto-objects that establish the perceptual organization of the scene. All computational mechanisms of the algorithm have direct neural correlates, and our results provide evidence for the interface theory of attention.

show abstract

“…More specifically, single-unit recordings with rhesus monkeys have revealed a heightened response to the medial axes of 2-D shapes from edge-detection neurons in V1 (Lee, 1996, 2003), and human participants have been found to display greater contrast sensitivity (a known proxy of activity in V1; Boynton, Demb, Glover, & Heeger, 1999) to Gabor patches as they neared the medial axis of the shape (Kovács, Fehér, & Julesz, 1998; Kovács & Julesz, 1994). Such findings suggest that the MAT formulation may support low-level shape processes such as figure-ground segmentation because it can specify all of the edges that are part of the object rather than the background (Ardila, Mihalas, von der Heydt, & Niebur, 2012; Li, 2000).…”

Section: Introductionmentioning

confidence: 99%

Skeletal representations of shape in human vision: Evidence for a pruned medial axis model

et al. 2019

View full text Add to dashboard Cite

A representation of shape that is low dimensional and stable across minor disruptions is critical for object recognition. Computer vision research suggests that such a representation can be supported by the medial axis—a computational model for extracting a shape's internal skeleton. However, few studies have shown evidence of medial axis processing in humans, and even fewer have examined how the medial axis is extracted in the presence of disruptive contours. Here, we tested whether human skeletal representations of shape reflect the medial axis transform (MAT), a computation sensitive to all available contours, or a pruned medial axis, which ignores contours that may be considered “noise.” Across three experiments, participants (N = 2062) were shown complete, perturbed, or illusory two-dimensional shapes on a tablet computer and were asked to tap the shapes anywhere once. When directly compared with another viable model of shape perception (based on principal axes), participants' collective responses were better fit by the medial axis, and a direct test of boundary avoidance suggested that this result was not likely because of a task-specific cognitive strategy (Experiment 1). Moreover, participants' responses reflected a pruned computation in shapes with small or large internal or external perturbations (Experiment 2) and under conditions of illusory contours (Experiment 3). These findings extend previous work by suggesting that humans extract a relatively stable medial axis of shapes. A relatively stable skeletal representation, reflected by a pruned model, may be well equipped to support real-world shape perception and object recognition.

show abstract

Medial axis generation in a model of perceptual organization

Cited by 10 publications

References 16 publications

A dual role for shape skeletons in human vision: perceptual organization and object recognition

A dual role for shape skeletons in human vision: perceptual organization and object recognition

A model of proto-object based saliency

Skeletal representations of shape in human vision: Evidence for a pruned medial axis model

Contact Info

Product

Resources

About