Abstract | ||
---|---|---|
We present an efficient method for detecting planar bilateral symmetries under perspective projection. The method uses local affine frames (LAFs) constructed on maximally stable extremal regions or any other affine covariant regions detected in the image to dramatically improve the process of detecting symmetric objects under perspective distortion. In contrast to the previous work no Hough transform, is used. Instead, each symmetric pair of LAFs votes just once for a single axis of symmetry. The time complexity of the method is n log(n), where n is the number of LAFs, allowing a near real-time performance. The proposed method is robust to background clutter and partial occlusion and is capable of detecting an arbitrary number of symmetries in the image. |
Year | Venue | Keywords |
---|---|---|
2007 | SCIA | symmetric object,perspective distortion,local affine frame,affine covariant region,n log,arbitrary number,efficient symmetry detection,perspective projection,lafs vote,efficient method,near real time,hough transform,computer and information science,time complexity |
Field | DocType | Volume |
Affine transformation,Computer science,Artificial intelligence,Time complexity,Homogeneous space,Perspective distortion,Combinatorics,Pattern recognition,Covariant transformation,Algorithm,Hough transform,Perspective (graphical),Maximally stable extremal regions | Conference | 4522 |
ISSN | Citations | PageRank |
0302-9743 | 16 | 0.74 |
References | Authors | |
15 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hugo Cornelius | 1 | 45 | 2.36 |
Michal Perd'och | 2 | 16 | 0.74 |
Jiri Matas | 3 | 4313 | 234.68 |
Gareth Loy | 4 | 627 | 42.88 |