Edge and Corner Detection by Photometric Quasi-Invariants
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-Time Imaging - Special issue on multi-dimensional image processing
Segmentation and guidance of multiple rigid objects for intra-operative endoscopic vision
WDV'05/WDV'06/ICCV'05/ECCV'06 Proceedings of the 2005/2006 international conference on Dynamical vision
A multi-level depiction method for painterly rendering based on visual perception cue
Multimedia Tools and Applications
Hi-index | 0.00 |
Photometric invariance is used in many computer vision applications.The advantage of photometric invariance is therobustness against shadows, shading, and illumination conditions.However, the drawbacks of photometric invarianceis the loss of discriminative power and the inherent instabilitiescaused by the non-linear transformations to computethe invariants.In this paper, we propose a new class of derivativeswhich we refer to as photometric quasi-invariants. Thesequasi-invariants share with full invariants the nice propertythat they are robust against photometric edges, such asshadows or specular edges. Further, these quasi-invariantsdo not have the inherent instabilities of full photometric invariants.We will apply these quasi-invariant derivativesin the context of photometric invariant edge detection andclassification. Experiments show that the quasi-invariantderivatives are stable and they significantly outperform thefull invariant derivatives in discriminative power.