Feedback and Surround Modulated Boundary Detection

Abstract

Edges are key components of any visual scene to the extent that we can recognise objects merely by their silhouettes. The human visual system captures edge information through neurons in the visual cortex that are sensitive to both intensity discontinuities and particular orientations. The "classical approach" assumes that these cells are only responsive to the stimulus present within their receptive fields, however, recent studies demonstrate that surrounding regions and inter-areal feedback connections influence their responses significantly. In this work we propose a biologicallyinspired edge detection model in which orientation selective neurons are represented through the first derivative of a Gaussian function resembling double-opponent cells in the primary visual cortex (V1). In our model we account for four kinds of receptive field surround, i.e. full, far, iso-and orthogonal-orientation, whose contributions are contrast-dependant. The output signal from V1 is pooled in its perpendicular direction by larger V2 neurons employing a contrast-variant centresurround kernel. We further introduce a feedback connection from higher-level visual areas to the lower ones.The results of our model on three benchmark datasets show a big improvement compared to the current nonlearning and biologically-inspired state-of-the-art algo-This work was funded by the Spanish Secretary of Research and Innovation (TIN2013-41751-P and TIN2013-49982-EXP) and the CERCA Programme from the Generalitat de Catalunya.

Contour Detection by Simulating the Curvature Cell in the Visual Cortex and its Application to Object Classification

“…They improved the performance of contour detection by using the multifeature-based surround inhibitions [13]. Similarly, Akbarinia and his colleagues proposed a biologically-inspired edge detection model [14]. They introduced four receptive field surround modulations into the boundary detection.…”

Superpixel Segmentation Based on Anisotropic Edge Strength

“…com/ASD) [44], and the neuronal structures in electron microscopy stacks dataset (NSEMS; http://brainiac2.mit.edu/isbi_challenge/home) [45]. In addition, in order to explore the impact of different kinds of edge strength on the segmentation accuracy, we also tested the SH methods that incorporate edge strength obtained by the structured forest edge (SH+SFE) method [28], the sparseness-constrained color-opponency (SH+SCO) method [26], the automated anisotropic Gaussian kernel (SH+AAGK) method [19], and the surrounded-modulation edge detection (SH+SED) method [27]. Furthermore, we also selected the widely used SLIC method [8] for comparison.…”

“…Note that there is one GT segmentation map for each microscopy image. In this experiment, we did not test the SH+SED method since it is not applicable to grayscale images [27]. For each method, the curves of average ASA and average UE values over all the 30 images with respect to different numbers of superpixels are shown in Figure 5e,f.…”

Biologically Inspired Hierarchical Contour Detection with Surround Modulation and Neural Connection

“…The structures of the receptive field for these V2 cells can be explained by the integration of the V1-cell receptive field. Based on this major physiological finding, we comprehensively considered selecting the elliptical Gaussian function along the optimal direction [ 43 ] to fit the characteristics of the V2-cell receptive field according to: …”