TY  - CONF
AU  - Josep M. Gonfaus
AU  - Theo Gevers
AU  - Arjan Gijsenij
AU  - Xavier Roca
AU  - Jordi Gonzalez
A2  - ICPR
PY  - 2012//
TI  - Edge Classification using Photo-Geo metric features
BT  - 21st International Conference on Pattern Recognition
SP  - 1497
EP  - 1500
N2  - Edges are caused by several imaging cues such as shadow, material and illumination transitions. Classification methods have been proposed which are solely based on photometric information, ignoring geometry to classify the physical nature of edges in images. In this paper, the aim is to present a novel strategy to handle both photometric and geometric information for edge classification. Photometric information is obtained through the use of quasi-invariants while geometric information is derived from the orientation and contrast of edges. Different combination frameworks are compared with a new principled approach that captures both information into the same descriptor. From large scale experiments on different datasets, it is shown that, in addition to photometric information, the geometry of edges is an important visual cue to distinguish between different edge types. It is concluded that by combining both cues the performance improves by more than 7% for shadows and highlights.
SN  - 1051-4651
SN  - 978-1-4673-2216-4
UR  - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6460426&tag=1
L1  - http://refbase.cvc.uab.es/files/GGG2012b.pdf
N1  - ISE
ID  - Josep M. Gonfaus2012
ER  -