Abstract | ||
---|---|---|
In this paper, we address the problem of representing objects using contours for the purpose of recognition. We propose a novel segmentation method for integrating a new contour matching energy into level set based segmentation schemes. The contour matching energy is represented by major components of Elliptic Fourier shape descriptors and serves as a shape prior to guide the curve evolution. The contours in training dataset serve as templates and are utilized to infer the category of an unknown image based on matching. Our method is evaluated on the UCF sports dataset and Caltech 101 dataset. Experiments show that our method achieves promising recognition accuracy and is robust to noisy low-level features and background clutter. |
Year | Venue | Keywords |
---|---|---|
2012 | ICPR | fourier transforms,unknown image matching,image representation,image matching,shape recognition,curve evolution,ucf sports dataset,contour prior decomposition,image segmentation,contour matching energy,level set-based segmentation schemes,caltech 101 dataset,training dataset,feature extraction,noisy low-level features,elliptic fourier shape descriptors,object representation |
Field | DocType | ISSN |
Active contour model,Computer vision,Caltech 101,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Clutter,Level set,Image segmentation,Feature extraction,Artificial intelligence | Conference | 1051-4651 |
ISBN | Citations | PageRank |
978-1-4673-2216-4 | 1 | 0.35 |
References | Authors | |
14 | 3 |