Abstract

A "width of a shape" concept considered in relation to variable-width objects is used as the integral shape descriptor for image recognition tasks. The approach to the definition of this concept is based on covering the figure of interest with certain-size disks. A function that defines the area of disk cover against the disk size is used as a shape descriptor. An analytical method for calculating the area of disk cover for polygonal figures is proposed. The possibility to approximate by polygonal figures binary raster images and objects with non-linear boundaries makes the approach universal. The proposed method is based on the medial representation of objects as a skeleton and a radial function. The method provides high accuracy and computational efficiency. The efficiency of the proposed shape descriptor is illustrated by the example of its application to the digital font recognition problem.

Full Text
Paper version not known

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 call

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.