Abstract
This paper presents a novel method to extract local features, which instead of calculating local extrema computes global maxima in a discretized scale-space representation. To avoid interpolating scales on few data points and to achieve perfect rotation invariance, two essential techniques, increasing the width of kernels in pixel and utilizing disk-shaped convolution templates, are adopted in this method. Since the size of a convolution template is finite and finite templates can introduce computational error into convolution, we sufficiently discuss this problem and work out an upper bound of the computational error. The upper bound is utilized in the method to ensure that all features obtained are computed under a given tolerance. Besides, the technique of relative threshold to determine features is adopted to reinforce the robustness for the scene of changing illumination. Simulations show that this new method attains high performance of repeatability in various situations including scale change, rotation, blur, JPEG compression, illumination change, and even viewpoint change.
Highlights
Local feature extraction is a fundamental technique for solving problems of computer vision, such as matching, tracking, and recognition
The traditional Harris corner detector [1] does not consider the variance of scale, which accounts for a drawback that it cannot be applied to matching features with different scales
Introducing a normalized derivative operator [3] into the scale-space theory [4], Lindeberg presented a framework for automatic scale selection, pointing out that a local maximum of some combination of normalized derivatives over scale reflects a characteristic length of a corresponding structure, and has a nice behavior under rescaling of the intensity pattern [3], which has been a principle for solving problems of feature extraction
Summary
Local feature extraction is a fundamental technique for solving problems of computer vision, such as matching, tracking, and recognition. Mikolajczyk presented a Harris–Laplacian method [7], which uses Harris functions of images in scale-space representation to extract interesting points and invokes Laplacian to select feature points as well as their precise scale parameters. We alternatively study a novel method, which, instead of LPE, extracts features in a discretized scale-space representation that has been constructed in advance, and name this new method as Global-Prior Extraction (GPE) To achieve this goal, the pivot techniques contributed in this paper are: (1) the algorithm of global-prior extraction, which improves repeatability of extracted features; (2) the disk-shaped convolution templates of increasing size in pixel, which is applied to realize rotation invariance and to obtain precise scales of local features; and (3) the threshold relative to the maximal feature response, which is employed to achieve illumination invariance.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
