Abstract
Articulated shapes are successfully represented by structural representations which are organized in the form of graphs of shape components. We present an alternative representation scheme which is equally powerful but does not require explicit modeling or discovery of structural relations. The key element in our scheme is a novel multi scale pixel-based distinctness measure which implicitly quantifies how rare a particular pixel is in terms of its geometry with respect to all pixels of the shape. The spatial distribution of the distinctness yields a partitioning of the shape into a set of regions. The proposed representation is a collection of size normalized probability distribution of the distinctness over regions over shape dependent scales. We test the proposed representation on a clustering task.
Highlights
Shape is a distinguishing attribute of an object frequently utilized in image processing and computer vision applications
Shapes of objects that articulate can be successfully represented by structural representations which are organized in the form of graphs of shape components
We proposed a new representation along with a clustering scheme to group articulated shapes in terms of similarity
Summary
Shape is a distinguishing attribute of an object frequently utilized in image processing and computer vision applications. Shapes of objects that articulate (referred to as articulated shapes) can be successfully represented by structural representations which are organized in the form of graphs of shape components. These components can be branches or critical points of the shape skeleton, subsets of the shape interior (commonly referred as parts), or fragments of shape boundary (commonly referred as contour fragments). In [12], the distance of shapes is measured using a new shape descriptor obtained by extending a contour-based descriptor to the shape interior and multi-objective optimization is applied to determine both the number of clusters and an optimal clustering result. In [16], a new distance measure that is defined between a single shape and a group of shapes is utilized in a soft k-means like clustering of shapes
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.
