Extraction of Illusory Contours by Perceptual Grouping (original) (raw)

Using a model of the human visual system to identify and enhance object contours in natural images

Segmentation of natural images depends on the ability to identify continuous contours that define the boundaries between objects. However, in many natural images (especially those captured in environments where the illumination is largely ambient) continuous contours can be difficult to identify. In spite of this, the human visual system efficiently perceives the contours along the boundaries of occluding objects. In fact, optical illusions, such as the Kanizsa triangle, demonstrate that the human visual system can 'see' object boundaries even when spatial intensity contrasts are totally absent from an image. In searching for the mechanism that generates these 'subjective contours' neurological researchers have found that the 2D image on the retina is mapped onto Layer 4 of the primary visual cortex (V1) and that there are lateral connections within the 6 layers of V1 that might subserve contour completion. This paper builds on a previous model of the early visual system (including the retina, the LGN and the simple cells of V1) by adding lateral interconnections to demonstrate how these interconnections might provide contour completion. Images are presented to show how this model enhances the detection of continuous spatial contours, thus contributing to the segmentation of natural images.

Does contour classification precede contour grouping in perception of partially visible figures?

Perception, 2007

When a figure is only partially visible and its contours represent a small fraction of total image contours (as when there is much background clutter), a fast contour classification mechanism may filter non-figure contours in order to restrict the size of the input to subsequent contour grouping mechanisms. The results of two psychophysical experiments suggest that the human visual system can classify figure from non-figure contours on the basis of a difference in some contour property (eg length, orientation, curvature, etc). While certain contour properties (eg orientation, curvature) require only local analysis for classification, other contour properties (eg length) may require more global analysis of the retinal image. We constructed a pyramid-based computational model based on these observations and performed two simulations of experiment 1: one simulation with classification enabled and the other simulation with classification disabled. The classification-based simulation gav...

A Fast Contour Detection Model Inspired by Biological Mechanisms in Primary Vision System

Frontiers in Computational Neuroscience, 2018

Compared to computer vision systems, the human visual system is more fast and accurate. It is well accepted that V1 neurons can well encode contour information. There are plenty of computational models about contour detection based on the mechanism of the V1 neurons. Multiple-cue inhibition operator is one well-known model, which is based on the mechanism of V1 neurons' non-classical receptive fields. However, this model is time-consuming and noisy. To solve these two problems, we propose an improved model which integrates some additional other mechanisms of the primary vision system. Firstly, based on the knowledge that the salient contours only occupy a small portion of the whole image, the prior filtering is introduced to decrease the running time. Secondly, based on the physiological finding that nearby neurons often have highly correlated responses and thus include redundant information, we adopt the uniform samplings to speed up the algorithm. Thirdly, sparse coding is introduced to suppress the unwanted noises. Finally, to validate the performance, we test it on Berkeley Segmentation Data Set. The results show that the improved model can decrease running time as well as keep the accuracy of the contour detection.

Perceptual Grouping for Contour Extraction

2004

This paper describes an algorithm that efficiently groups line segments into perceptually salient contours in complex images. A measure of affinity between pairs of lines is used to guide group formation and limit the branching factor of the contour search procedure. The extracted contours are ranked, and presented as a contour hierarchy. Our algorithm is able to extract salient contours in the presence of texture, clutter, and repetitive or ambiguous image structure. We show experimental results on a complex line-set.

On the perception of illusory contours

Vision Research, 1994

Illusory contours are invoked by the visual system to account for otherwise inexplicable gaps in the image. We report three sets of novel observations on illusory contours. First, when an illusory square is superimposed on a checkerboard pattern there is a considerable enhancement of the contours so long as they are exactly coincident with the borders of the checks. If the checks are misaligned, on the other hand, the illusory contours associated with the pacman edges disappear and a novel percept emerges: the contours of the checks nearest to the illusory square appear enhanced. This result implies that subjective contours are generated by intermediate-level contour interactions rather than the topdown processes of three-dimensional interpretation. Second, we find that steady fixation for as little as 4 set leads to a complete disappearance of the enhanced illusory contours caused, presumably, by adaptation or "fatigue" of cells that signal these contours. Such adaptation occurred even when the illusory contours were rendered invisible by displaying them on a misaligned checkerboard, suggesting that the adaptation occurs prior to the vetoing of the signal by the checks. Third, we found that illusory contours persist for a surprisingly long time (0.3 set) after the inducing elements have been switched off. These results suggest that the stimuli we have designed ("enhanced illusory contours") might provide a novel probe for dissecting different stages involved in the processing of illusory contours and for understanding how the visual system combines different types of contours to construct object boundaries.

A contour detection method based on some knowledges of the visual system

We propose a contour detection method based on the mechanisms from biological visual perception. The temporal analysis of image is the basis of the model. The temporal notion means that the static image is transformed into a data flow. Each element of the flow is treated independently from the others. Our aim is image segmentation through contour detection. The model is composed of a succession of five stages: noise reduction, asynchronous processing, isotropic filtering and adaptive smoothing, dynamic thresholding, and temporal integration. To evaluate the proposed approach, objective and subjective analyses are performed on synthetic and actual images.

A Simple Scheme for Contour Detection

Proc. of the Conference on Computer Vision …, 2006

Abstract: We present a computationally simple and general purpose scheme for the detection of all salient object con-tours in real images. The scheme is inspired by the mechanism of surround influence that is exhibited in 80% of neurons in the primary visual cortex of primates. It is ...

Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape

Neural Computation, 2001

A recent neural model of illusory contour formation is based on a distribution of natural shapes traced by particles moving with constant speed in directions given by Brownian motions. The input to that model consists of pairs of position and direction constraints and the output consists of the distribution of contours joining all such pairs. In general, these contours will not be closed and their distribution will not be scale-invariant. In this paper, we show how to compute a scale-invariant distribution of closed contours given position constraints alone and use this result to explain a well known illusory contour effect.

A computational model of temporal segmentation and the perception of phantom contours

Australian Journal of Psychology, 2008

The timing of events can influence spatial segmentation. Neighbouring regions flickering asynchronously at a high temporal frequency appear identical, but the visual system signals a 'phantom contour' between them. Using psychophysical procedures, we determined the spatial limitations of this form of temporal segmentation across the visual field. These limitations correspond closely to receptive field diameters of neurons in primary visual cortex (V1), and are also consistent with the spatial limitations of motion detection. Here, we propose a computational model in which the neural signal for phantom contours originates from individual neurons with receptive fields that are space-time separable, like those mapped in cat and macaque V1. Similar units are also employed in the first stages of models for the perception of local motion. The correspondence between theoretical models of temporal segmentation and motion perception in the human visual system, as well as psychophysical evidence that they have similar spatial limitations, support the notion that these processes are mediated by a common neural substrate situated in early in visual cortex.

Predicting Illusory Contours Without Extracting Special Image Features

Frontiers in Computational Neuroscience

Boundary completion is one of the desired properties of a robust object boundary detection model, since in real-word images the object boundaries are commonly not fully and clearly seen. An extreme example of boundary completion occurs in images with illusory contours, where the visual system completes boundaries in locations without intensity gradient. Most illusory contour models extract special image features, such as L and T junctions, while the task is known to be a difficult issue in real-world images. The proposed model uses a functional optimization approach, in which a cost value is assigned to any boundary arrangement to find the arrangement with minimal cost. The functional accounts for basic object properties, such as alignment with the image, object boundary continuity, and boundary simplicity. The encoding of these properties in the functional does not require special features extraction, since the alignment with the image only requires extraction of the image edges. The boundary arrangement is represented by a border ownership map, holding object boundary segments in discrete locations and directions. The model finds multiple possible image interpretations, which are ranked according to the probability that they are supposed to be perceived. This is achieved by using a novel approach to represent the different image interpretations by multiple functional local minima. The model is successfully applied to objects with real and illusory contours. In the case of Kanizsa illusion the model predicts both illusory and real (pacman) image interpretations. The model is a proof of concept and is currently restricted to synthetic gray-scale images with solid regions.