Sciweavers

21 search results - page 1 / 5
» Maximally Stable Colour Regions for Recognition and Matching
Sort
View
CVPR
2007
IEEE
14 years 6 months ago
Maximally Stable Colour Regions for Recognition and Matching
This paper introduces a novel colour-based affine covariant region detector. Our algorithm is an extension of the maximally stable extremal region (MSER) to colour. The extension ...
Per-Erik Forssén
ECCV
2006
Springer
14 years 6 months ago
Maximally Stable Local Description for Scale Selection
Scale and affine-invariant local features have shown excellent performance in image matching, object and texture recognition. This paper optimizes keypoint detection to achieve sta...
Cordelia Schmid, Gyuri Dorkó
CVPR
2007
IEEE
14 years 6 months ago
Principal Curvature-Based Region Detector for Object Recognition
This paper presents a new structure-based interest region detector called Principal Curvature-Based Regions (PCBR) which we use for object class recognition. The PCBR interest ope...
Hongli Deng, Wei Zhang, Eric N. Mortensen, Thomas ...
ICCV
2009
IEEE
13 years 2 months ago
Building recognition using sketch-based representations and spectral graph matching
In this work, we address the problem of building recognition across two camera views with large changes in scales and viewpoints. The main idea is to construct a semantically rich...
Yu-Chia Chung, Tony X. Han, Zhihai He
ICCV
2007
IEEE
14 years 6 months ago
Shape Descriptors for Maximally Stable Extremal Regions
This paper introduces an affine invariant shape descriptor for maximally stable extremal regions (MSER). Affine invariant feature descriptors are normally computed by sampling the...
David G. Lowe, Per-Erik Forssén