CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2005 vol.27 Issue No.04 - April
Issue No.04 - April (2005 vol.27)
Theo Gevers , IEEE
Joost van de Weijer , IEEE
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2005.75
Feature detection is used in many computer vision applications such as image segmentation, object recognition, and image retrieval. For these applications, robustness with respect to shadows, shading, and specularities is desired. Features based on derivatives of photometric invariants, which we will call full invariants, provide the desired robustness. However, because computation of photometric invariants involves nonlinear transformations, these features are unstable and, therefore, impractical for many applications. We propose a new class of derivatives which we refer to as quasi-invariants. These quasi-invariants are derivatives which share with full photometric invariants the property that they are insensitive for certain photometric edges, such as shadows or specular edges, but without the inherent instabilities of full photometric invariants. Experiments show that the quasi-invariant derivatives are less sensitive to noise and introduce less edge displacement than full invariant derivatives. Moreover, quasi-invariants significantly outperform the full invariant derivatives in terms of discriminative power.
Edge and feature detection, invariants, color.
Theo Gevers, Joost van de Weijer, "Edge and Corner Detection by Photometric Quasi-Invariants", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.27, no. 4, pp. 625-630, April 2005, doi:10.1109/TPAMI.2005.75