Abstract
Contour detection has been extensively investigated as a fundamental problem in computer vision. In this study, a biologically-inspired candidate weighting framework is proposed for the challenging task of detecting meaningful contours. In contrast to previous models that detect contours from pixels, a modified superpixel generation processing is proposed to generate a contour candidate set and then weigh the candidates by extracting hierarchical visual cues. We extract the low-level visual local cues to weigh the contour intrinsic property and mid-level visual cues on the basis of Gestalt principles for weighting the contour grouping constraint. Experimental results tested on the BSDS benchmark show that the proposed framework exhibits promising performances to capture meaningful contours in complex scenes.
Highlights
Contour detection has remained a fundamental problem in computer vision that has been intensively studied in the past fifty years
A biologically-inspired candidate weighting (BICW) framework is proposed for contour detection
Neurons in primary visual cortex (V1 or striate cortex) respond to oriented luminance and chromatic stimulation, which is expressed as a low-level visual process
Summary
Contour detection has remained a fundamental problem in computer vision that has been intensively studied in the past fifty years. In a complex natural scene, the components that have abundant and specific attributes are more prominent and are easier to isolate from the background This problem of extracting and integrating structural information is called perceptual grouping. A series of neurophysiological supporting evidence of these properties has been studied in [33,34,35,36] (see [37] for a review) Inspired by these biological bases, many works for contour detection have been developed, for example [38,39,40,41,42,43,44,45,46,47,48]. We propose a biologically-inspired method of extracting hierarchical visual cues to weight the candidates.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
