Abstract
Based on the topographic description of slope districts, images can be segmented into a set of regions that is invariant to uniform monotonic scalings of the image. Whereas most previous work relating to slope districts has been restricted to ideal continuous smooth surfaces, this paper describes a robust technique for extracting slope districts from discrete images which is insensitive to variations in the topology of the image. In addition, the image is smoothed over a range of scales to produce a hierarchical description in terms of linked slope districts. At each scale the slope districts are described by attributes such as their image curvature, edge location, and gray-level volume. This image representation is intended as input to subsequent stages of image analysis such as feature grouping and model matching.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Journal of Visual Communication and Image Representation
Disclaimer: 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.