Experimental observations suggest that contour integration may take place in V1. However, there has yet to be a model of contour integration that only uses known V1 elements, operations, and connection patterns. This paper introduces such a model, using orientation selective cells, local cortical circuits, and horizontal intra-cortical connections. The model is composed of recurrently connected excitatory neurons and inhibitory interneurons, receiving visual input via oriented receptive fields resembling those found in primary visual cortex. Intracortical interactions modify initial activity patterns from input, selectively amplifying the activities of edges that form smooth contours in the image. The neural activities produced by such interactions are oscillatory and edge segments within a contour oscillate in synchrony. It is shown analytically and empirically that the extent of contour enhancement and neural synchrony increases with the smoothness, length, and closure of contours, a...

We study image segmentation on the basis of locally excitatory globally inhibitory oscillator networks (LEGION), whereby the phases of oscillators encode the binding of pixels. We introduce a potential for each oscillator so that only those oscillators with strong connections from their neighborhood can develop high potentials. Based on the concept of potential, a solution to remove noisy regions in an image is proposed for LEGION, so that it suppresses the oscillators corresponding to noisy regions, without affecting those corresponding to major regions. We show analytically that the resulting oscillator network separates an image into several major regions, plus a background consisting of all noisy regions, and illustrate network properties by computer simulation. The network exhibits a natural capacity in segmenting images. The oscillatory dynamics leads to a computer algorithm, which is applied successfully to segmenting real graylevel images. A number of issues regarding biological plausibility and perceptual organization are discussed. We argue that LEGION provides a novel and effective framework for image segmentation and figure-ground segregation. DeLiang Wang and David Terman Image Segmentation 1.

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object they belong. Current computational systems that perform this operation are based on predefined grouping heuristics. We describe a system called MAGIC that learns how to group features based on a set of presegmented examples. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of finding nonintuitive structural regularities in images. Grouping is performed by a relaxation network that attempts to dynamically bind related features. Features transmit a complex-valued signal (amplitude and phase) to one another; binding can thus be represented by phase locking related features. MAGIC's training procedure is a generalizatio...

How does the brain group together different parts of an object into a coherent visual object representation? Different parts of an object may be processed by the brain at different rates and may thus become desynchronized. Perceptual framing is a process that resynchronizes cortical activities corresponding to the same retinal object. A neural network model is presented that is able to rapidly resynchronize desynchronized neural activities. The model provides a link between perceptual and brain data. Model properties quantitatively simulate perceptual framing data, including psychophysical data about temporal order judgments and the reduction of threshold contrast as a function of stimulus length. Such a model has earlier been used to explain data about illusory contour formation, texture segregation, shape-from-shading, 3-D vision, and cortical receptive fields. The model hereby shows how many data may be understood as manifestations of a cortical grouping process that can rapidly res...

We present a cortical-based model for computing the perceptual salience of contours embedded in noisy images. It has been suggested (Gilbert, 1992; Field, Hayes & Hess, 1993) that horizontal intra-cortical connections in primary visual cortex may modulate contrast detection thresholds and pre-attentive "popout ". In our model, horizontal connections mediate context-dependent facilitatory and inhibitory interactions among oriented cells. Strongly facilitated cells undergo temporal synchronization; and perceptual salience is determined by the level of synchronized activity. The model accounts for a range of reported psychophysical and physiological effects of contour salience (Polat & Sagi, 1993, 1994; Kapadia, Ito, Gilbert & Westheimer, 1995; Field et al., 1993; Kovács, Polat & Norcia, 1996; Pettet, McKee & Grzywacz, 1996). In particular, the model proposes that intrinsic properties of synchronization account for the increased salience of smooth, closed contours (Kovács & Julesz, 1993, ...

Although perseveration---the inappropriate repetition of previous responses---is quite common among patients with neurological damage, relatively few detailed computational accounts of its various forms have been put forth. A particularly well-documented variety involves the pattern of errors made by "optic aphasic" patients, who have a selective deficit in naming visually-presented objects. Based on our previous work in modeling impaired reading for meaning in deep dyslexia, we develop a connectionist simulation of visual object naming. The major extension in the present work is the incorporation of short-term correlational weights that bias the network towards reproducing patterns of activity that have occurred on recently preceding trials. Under damage, the network replicates the complex semantic and perseverative effects found in the optic aphasic error pattern. Further analysis reveals that the perseverative effects are strongest when the lesions are near or within semanti...

We propose an image segmentation method based on texture analysis. Our method is composed of two parts. The first part determines a novel set of texture features derived from a Gaussian--Markov random fields (GMRF) model. Unlike a GMRFbased approach, our method does not employ model parameters as features or require the extraction of features for a fixed set of texture types a priori. The second part is a two-dimensional (2--D) array of locally excitatory globally inhibitory oscillator networks (LEGION). After being filtered for noise suppression, features are used to determine the local couplings in the network. When LEGION runs, the oscillators corresponding to the same texture tend to synchronize, whereas different texture regions tend to correspond to distinct phases. In simulations, a large system of differential equations is solved for the first time using a recently proposed method for integrating relaxation oscillator networks. We provide results on real texture images to demonstrate the performance of our method. Index Terms---Dynamical systems, Gaussian Markov random fields, LEGION, neural networks, relaxation oscillators, texture segmentation. I.

We present a recurrent neural network for feature binding and sensory segmentation, the competitive layer model (CLM). The CLM uses topographically structured competitive and cooperative interactions in a layered network to partition a set of input features into salient groups. The dynamics is formulated within a standard additive recurrent network with linear threshold neurons. Contextual relations among features are coded by pairwise compatibilities which define an energy function to be minimized by the neural dynamics. Due to the usage of dynamical winner-take-all circuits the model gains more flexible response properties than spin models of segmentation by exploiting amplitude information in the grouping process. We prove analytic results on the convergence and stable attractors of the CLM, which generalize earlier results on winner-take-all networks, and incorporate deterministic annealing for robustness against local minima. The piecewise linear dynamics of the CLM allows a linear eigensubspace analysis which we use to analyze the dynamics of binding in conjunction with annealing. For the example of contour detection we show how the CLM can integrate figure-ground segmentation and grouping into a unified model.

Advances in visualization technology and specialized graphic workstations allow clinicians to virtually interact with anatomical structures contained within sampled medical-image datasets. A hindrance to the effective use of this technology is the difficult problem of image segmentation. In this paper, we utilize a recently proposed oscillator network called the locally excitatory globally inhibitory oscillator network (LEGION) whose ability to achieve fast synchrony with local excitation and desynchrony with global inhibition makes it an effective computational framework for grouping similar features and segregating dissimilar ones in an image. We extract an algorithm from LEGION dynamics and propose an adaptive scheme for grouping. We show results of the algorithm to two-dimensional (2-D) and threedimensional (3-D) (volume) computerized topography (CT) and magnetic resonance imaging (MRI) medical-image datasets. In addition, we compare our algorithm with other algorithms for medical-...

A network of Wilson-Cowan oscillators is constructed, and its emergent properties of synchronization and desynchronization are investigated by both computer simulation and formal analysis. The network is a two-dimensional matrix, where each oscillator is coupled only to its neighbors. We show analytically that a chain of locally coupled oscillators (the piece-wise linear approximation to the Wilson-Cowan oscillator) synchronizes, and present a technique to rapidly entrain finite numbers of oscillators. The coupling strengths change on a fast time scale based on a Hebbian rule. A global separator is introduced which receives input from and sends feedback to each oscillator in the matrix. The global separator is used to desynchronize different oscillator groups. Unlike many other models, the properties of this network emerge from local connections, that preserve spatial relationships among components, and are critical for encoding Gestalt principles of feature grouping. The ability to sy...