Abstract
In this paper, we present three different smart mapping schemes that improve on the quickness of dissimilarity detection between images. We call the mapping schemes smart because the mapping order is setup intelligently to detect dissimilarity quickly by concentrating its search near the center of the images, which is usually the region of interest in a given scene. Thus, smart mapping is well suited for images when the differences between them are expected to be concentrated near the center of the image. We construct a mapping vector (MV) that contains an ordered list of point mappings which is employed to map points between images in an efficient manner. The focus in this paper is on applying the three different smart mapping schemes to binary images. Furthermore, we test three different mapping densities with each smart mapping scheme and analyze the results. Tests are conducted on two image sets and dissimilarity detection results are compared to results obtained via random mapping, which had been shown to be extremely fast, as predicted by the probabilistic matching model for binary images (PMMBI). We show that by employing smart mapping a great improvement in dissimilarity detection quickness is possible when dissimilarity between images is concentrated near the center of the scene.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.