Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2011-04-14
T-PAMI vol. 30 no. 12, pp. 2188-2203, 2008
Computer Science
Computer Vision and Pattern Recognition
The work excluding {\S}V and {\S}VI has first appeared in 2005 ICCV: Aslan, C., Tari, S.: An Axis-Based Representation for Rec
Scientific paper
We present a new skeletal representation along with a matching framework to address the deformable shape recognition problem. The disconnectedness arises as a result of excessive regularization that we use to describe a shape at an attainably coarse scale. Our motivation is to rely on the stable properties of the shape instead of inaccurately measured secondary details. The new representation does not suffer from the common instability problems of traditional connected skeletons, and the matching process gives quite successful results on a diverse database of 2D shapes. An important difference of our approach from the conventional use of the skeleton is that we replace the local coordinate frame with a global Euclidean frame supported by additional mechanisms to handle articulations and local boundary deformations. As a result, we can produce descriptions that are sensitive to any combination of changes in scale, position, orientation and articulation, as well as invariant ones.
Aslan Cagri
Erdem Ahmet
Erdem Esra
Tari Sibel
No associations
LandOfFree
Disconnected Skeleton: Shape at its Absolute Scale does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Disconnected Skeleton: Shape at its Absolute Scale, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Disconnected Skeleton: Shape at its Absolute Scale will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-166701