Edge and corner detection by photometric quasi-invariants

• Published in: IEEE transactions on pattern analysis and machine intelligence 2005-04, Vol.27 (4), p.625-630
• Main Authors: van de Weijer, J., Gevers, T., Geusebroek, J.-M.
• Format: Article
• Language: English
• Subjects: Algorithms; Application software; Applied sciences; Artificial Intelligence; color; Computer Science; Computer science; control theory; systems; Computer vision; Computer Vision and Pattern Recognition; Corner detection; Derivatives; Exact sciences and technology; Feature based; Image edge detection; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image retrieval; Image segmentation; Index Terms- Edge and feature detection; Information Storage and Retrieval - methods; Invariants; Object detection; Object recognition; Optical reflection; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; Photometry; Photometry - methods; Reproducibility of Results; Robustness; Sensitivity and Specificity; Shadows
• ISSN: 0162-8828; 1939-3539
• DOI: 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 is called 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.