Enhancement of Perceptually Salient Contours using a Parallel Artificial Cortical Network

Abstract

In this paper we present a parallel artificial cortical network inspired by the Human visual system, which enhances the salient contours of an image. The network consists of independent processing elements, which are organized into hypercolumns. They process concurrently the distinct orientations of all the edges of the image. These processing elements are a new set of orientation kernels appropriate for the discrete lattice of the hypercolumns. The Gestalt laws of proximity and continuity that describe the process of saliency extraction in the human brain are encoded by means of weights. These weights interconnect the kernels according to a novel connection pattern based on co-exponentiality. The output of every kernel is modulated by the outputs of its neighboring kernels, according to a new affinity function. This function takes into account the degree of difference between the facilitation of the two lobes of the kernel. Saliency enhancement results as a consequence of the local interactions between the kernels. The network was tested on real and synthetic images and displays promising results for both. Comparisons with other methods with the same scope, demonstrate that the proposed method performs adequately. Furthermore it exhibits O(N) complexity with execution times that have never been reported by any other method so far, even though it is executed on a conventional PC.

A single functional model of drivers and modulators in cortex

“…Both these types of connections are seen in cortex (Hunt et al, 2011). The pattern of lateral connectivity between boundary-edge detecting prediction neurons is similar to that used in many previous models of contour detection (e.g., Ben-Shahar and Zucker, 2004;Hansen and Neumann, 2008;Huang et al, 2009;Li, 1998;Mundhenk and Itti, 2005;Parent and Zucker, 1989;Ursino and La Cara, 2004;Vonikakis et al, 2006;Yen and Finkel, 1998).…”

Potential roles of the interaction between model V1 neurons with orientation-selective and non-selective surround inhibition in contour detection

“…From a physiological point of view, the goal of this study is not to develop a contour detection model incorporated with the full V1 mechanisms including surround inhibition, spatial facilitation, feedback modulation from higher levels, temporal dynamics, etc. (Field et al, 1993; Fitzpatrick, 2000; Seriès et al, 2003; Ursino and La Cara, 2004; Vonikakis et al, 2006; Dakin and Baruch, 2009; Huang et al, 2009; Chen et al, 2014), but to clarify the different roles of orientation-selective and non-selective surround inhibition of V1 neurons in the specific task of extracting salient contours of objects from cluttered background. As the basis of this study, we demonstrated in the very beginning of this paper that, in general, V1 neurons with non-selective surround inhibition exhibit better overall performance measure due to its markedly superior ability in suppressing noised background.…”

Image Segmentation Using a Sparse Coding Model of Cortical Area V1

“…For this reason, numerous neural network approaches have been proposed that are inspired by the physiology of the primary visual cortex (Ben-Shahar and Zucker, 2004;Grigorescu et al, 2003Grigorescu et al, , 2004Hansen and Neumann, 2008;Huang et al, 2009;Li, 1998;Mundhenk and Itti, 2005;Papari et al, 2007;Papari and Petkov, 2011;Petkov and Westenberg, 2003;Tang et al, 2007a,b;Ursino and La Cara, 2004;Vonikakis et al, 2006;Zeng et al, 2011a,b). A neuron in such a model has a classical receptive field (cRF), often defined using a Gabor function, that receives input from the image.…”