Abstract
Obtaining good quality image features is of remarkable importance for most computer vision tasks. It has been demonstrated that the first layers of the human visual cortex are devoted to feature detection. The need for these features has made line, segment, and corner detection one of the most studied topics in computer vision. HT3D is a recent variant of the Hough transform for the combined detection of corners and line segments in images. It uses a 3D parameter space that enables the detection of segments instead of whole lines. This space also encloses canonical configurations of image corners, transforming corner detection into a pattern search problem. Spiking neural networks (SNN) have previously been proposed for multiple image processing tasks, including corner and line detection using the Hough transform. Following these ideas, this paper presents and describes in detail a model to implement HT3D as a Spiking Neural Network for corner detection. The results obtained from a thorough testing of its implementation using real images evince the correctness of the Spiking Neural Network HT3D implementation. Such results are comparable to those obtained with the regular HT3D implementation, which are in turn superior to other corner detection algorithms.
Highlights
The Hough Transform (HT) (Hough, 1959) is a mathematical technique used as a means to detect lines and other features in computer images
The Standard HT for straight line detection does not provide a direct representation of line segments, since feature points are mapped to infinite lines in the parameter space (Duda and Hart, 1972)
These connections allow “enabling” only certain neurons of the endpoint detection layer and ensure that every detected point corresponds to an edge pixel. This strategy for locating segment endpoints in the image space is similar to the one presented by Barrett and Petersen (2001). Despite this approach differs from the final stage of the original HT3D algorithm, the idea of a reverse voting from the Hough space to the image space adapts in a direct and simple way to Spiking neural networks (SNN) and produces similar results to the ones obtained by the regular implementation of HT3D
Summary
It has been demonstrated that the first layers of the human visual cortex are devoted to feature detection The need for these features has made line, segment, and corner detection one of the most studied topics in computer vision. HT3D is a recent variant of the Hough transform for the combined detection of corners and line segments in images. Spiking neural networks (SNN) have previously been proposed for multiple image processing tasks, including corner and line detection using the Hough transform. Following these ideas, this paper presents and describes in detail a model to implement HT3D as a Spiking Neural Network for corner detection.
Sign-in/Register to view highlights & summary 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.
