A Biologically Motivated Multiresolution Approach to Contour Detection

Abstract

Standard edge detectors react to all local luminance changes, irrespective of whether they are due to the contours of the objects represented in a scene or due to natural textures like grass, foliage, water, and so forth. Moreover, edges due to texture are often stronger than edges due to object contours. This implies that further processing is needed to discriminate object contours from texture edges. In this paper, we propose a biologically motivated multiresolution contour detection method using Bayesian denoising and a surround inhibition technique. Specifically, the proposed approach deploys computation of the gradient at different resolutions, followed by Bayesian denoising of the edge image. Then, a biologically motivated surround inhibition step is applied in order to suppress edges that are due to texture. We propose an improvement of the surround suppression used in previous works. Finally, a contour-oriented binarization algorithm is used, relying on the observation that object contours lead to long connected components rather than to short rods obtained from textures. Experimental results show that our contour detection method outperforms standard edge detectors as well as other methods that deploy inhibition. research activity has been focused mainly on information theory, signal theory, and signal and image processing and their applications to both telecommunications systems and remote sensing.

Image Segmentation Using a Sparse Coding Model of Cortical Area V1

“…This produced an F-score of 62 on the BSDS300 benchmark. While there may be scope for improving this result by using more sophisticated methods of combining results across scales (Papari et al, 2007;Ren, 2008) this results suggest that the proposed algorithm is not limited significantly by sensitivity to scale, and that incorporating other cues to segmentation, such as texture and colour, may be more effective at…”

“…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.…”

Early Recurrence Improves Edge Detection

“…Experiments using real images confirmed that self-inhibition improves edge detection, leading to much cleaned contour maps compared with Canny and Gabor energy edge detectors. Investigation of selfinhibition has been extended into multi-scale analysis in [2,3] with different applications. More recently self-inhibition has been re-visited with a refined center-surround inhibition scheme [19].…”

Adaptive Pseudo Dilation for Gestalt Edge Grouping and Contour Detection

“…Examples of such quantities are the gradient magnitude [1], Gabor energy [26], phase congruency [14], template matching [18], and texture gradient [19]. In our experiments, is a quantity called contourness, introduced in [29] and [58] with the purpose of suppressing texture, and successively improved in [59]- [61]. Thinning by nonmaxima suppression, which is also a local operation, is included in the computation of .…”