Interest point detection using rank order LoG filter

• A novel rank order LoG (ROLG) filter is proposed.
• The ROLG filter is robust to abrupt variations.
• The edge response is suppressed by the ROLG filter.
• The ROLG filter does not produce spurious peaks around blobs.
• The resulting interest point detector outperforms the state-of-the-art.

This paper proposes a novel nonlinear filter, named rank order Laplacian of Gaussian (ROLG) filter, based on which a new interest point detector is developed. The ROLG filter is a weighted rank order filter. It is used to detect the image local structures where a significant majority of pixels are brighter or darker than a significant majority of pixels in their corresponding surroundings. Compared to linear filter based detectors, e.g. SIFT detector, the proposed rank order filter based detector is more robust to abrupt variations of images caused by illumination and geometric changes. Experiments on the benchmark databases demonstrate that the proposed ROLG detector achieves superior performance comparing to four state-of-the-art detectors. Evaluation experiments are also conducted on face recognition problems. The results on five face databases further demonstrate that the ROLG detector significantly outperforms the other detectors.