Contrast Invariant Interest Point Detection by Zero-Norm LoG Filter

• Published in: IEEE transactions on image processing Vol. 25; no. 1; pp. 331 - 342
• Main Authors: Miao, Zhenwei, Jiang, Xudong, Yap, Kim-Hui
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2016
• Subjects: Detectors; face recognition; Feature extraction; Illumination; Image contrast; Image detection; image matchingzero-norm; Image processing; Image segmentation; Interest point detection; Invariants; Laplacian of Gaussian filter; Lighting; Matching; Noise; Object recognition; Robustness; Transmission line matrix methods; zero-norm; face recognition; Interest point detection; image matching; Laplacian of Gaussian filter
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2015.2470598

The Laplacian of Gaussian (LoG) filter is widely used in interest point detection. However, low-contrast image structures, though stable and significant, are often submerged by the high-contrast ones in the response image of the LoG filter, and hence are difficult to be detected. To solve this problem, we derive a generalized LoG filter, and propose a zero-norm LoG filter. The response of the zero-norm LoG filter is proportional to the weighted number of bright/dark pixels in a local region, which makes this filter be invariant to the image contrast. Based on the zero-norm LoG filter, we develop an interest point detector to extract local structures from images. Compared with the contrast dependent detectors, such as the popular scale invariant feature transform detector, the proposed detector is robust to illumination changes and abrupt variations of images. Experiments on benchmark databases demonstrate the superior performance of the proposed zero-norm LoG detector in terms of the repeatability and matching score of the detected points as well as the image recognition rate under different conditions.