Bi-directional Shape Correspondences (BSC)

dc.contributor.authorAbdulrahman, Ibraheem
dc.date.accessioned2023-05-13T18:01:35Z
dc.date.available2023-05-13T18:01:35Z
dc.date.issued2014-11
dc.description.abstractWe propose Bidirectional Shape Correspondence (BSC) as a possible improvement on the famous shape contexts (SC) framework. Our proposals derive from the observation that the SC framework enforces a one-to-one correspondence between sample points, and that this leads to two possible drawbacks. First, this denies the framework the opportunity to effect advantageous many-to-many matching between points on the two shapes being compared. Second, this calls for the Hungarian algorithm which unfortunately usurps cubic time. While the dynamic-space-warping dynamic programming algorithm has provided a standard solution to the first problem above, it demands quintic time for general multi-contour shapes, and w times quadratic time for the special case of single-contour shapes, even after an heuristic search window of width w has been chosen. Therefore, in this work, we propose a simple method for computing "many-to-many" correspondences for the class of all 2-d shapes in quadratic time. Our approach is to explicitly let each point on the first shape choose a best match on the second shape, and vice versa. Along the way, we also propose the use of data-clustering techniques for dealing with the outliers problem, and, from another viewpoint, it turns out that this clustering can be seen as an autonomous, rather than pre-computed, sampling of shape boundary.en_US
dc.identifier.urihttps://ir.oauife.edu.ng/123456789/5607
dc.language.isoesen_US
dc.publisherAbdulrahman Ibraheemen_US
dc.subjectBi-directional Shape Correspondencesen_US
dc.subjectshape contextsen_US
dc.subjectHungarian algorithmen_US
dc.subjectdynamic-space-warpingen_US
dc.subjectdynamic programming algorithmen_US
dc.titleBi-directional Shape Correspondences (BSC)en_US
dc.typeConference paperen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
citation-220553488 (1).txt
Size:
1.72 KB
Format:
Plain Text
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections