In this paper we present a novel approach to model perceptual grouping based on phase and frequency synchronization in a network of coupled Kuramoto oscillators. Transferring the grouping concept from the Competitive Layer Model (CLM) to a network of Kuramoto oscillators, we preserve the excellent grouping capabilities of the CLM, while dramatically improving the convergence rate, robustness to...

We introduce planar grouping, a technique where planar relationship information is gathered for a set of rigid points. This information is used to accelerate affine transformations and clipping. The planar grouping technique is an optimization problem, implemented in a best-first greedy search. We present two error metrics, one simple and fast, one based on the quadric error metric (QEM) to ach...

It has been recognized that there is a need for a language mechanism that support reuse of collections of related classes. Existing approaches either use an enclosing class for this purpose, or introduce a special purpose, new language construct. In this paper we explore the use of packages for the grouping of related classes. Ordinary packages are already grouping of classes, so we explore the...

A new contour extraction method is described in this paper. It is based on organization of the image data using perceptual grouping rules. and is therefore largely domain independent. The first step is to form an intermediate line segment representation of the contours by grouping edge points in paraBe and at different re~so~ution.s, The main feature of the hne .segn~ent extra~ti[~n process is ...

We propose the Gabor lattice as a new stimulus designed to deal with multiple organizations in perceptual grouping, allowing both comparison between psychophysical data and neural findings and a systematic investigation of grouping based on several low-level characteristics and their interactions. A Gabor lattice is a geometric lattice with Gabor patches, evoking a multistable global orientatio...

In typical studies of node grouping detection, the grouping is presumed to have a certain type of correlation with the network structure (e.g., densely connected groups of nodes that are loosely connected in between). People have defined different fitness measures (modularity, conductance, etc.) to quantify such correlation, and group the nodes by optimizing a certain fitness measure. However, ...

It has often been suggested that Gestalt-like visual grouping processes may operate preattentively, but Mack and Rock (1998) suggested that no visual grouping takes place under "inattention." We introduced a new method to assess this. While participants performed a demanding change-detection task on a small matrix at fixation, task-irrelevant background elements were arranged by color sinilarit...

We investigated the extent to which intramodal visual perceptual grouping influences the multisensory integration (or grouping) of auditory and visual motion information. Participants discriminated the direction of motion of two sequentially presented sounds (moving leftward or rightward), while simultaneously trying to ignore a task-irrelevant visual apparent motion stream. The principles of p...

We present a series of experiments whose results show strong similarities between textural grouping and motion experiments. A family of stimuli consisting of elements of different colors, luminancepolarity, and orientation are used in experiments in both eliciting textural grouping and detection of apparent motion. Among the similarities are that the orientation attribute is a weaker attribute ...

Perceptual grouping plays a critical role in both human and computer vision. However, with the object categorization community’s preoccupation with object detection, interest in perceptual grouping has waned. The reason for this is clear: the object-independent, mid-level shape priors that form the basis of perceptual grouping are subsumed by the object-dependent, high-level shape priors define...