A Feature-based Image Normalization Technique for Handling Geometric Distortions
Mohamed Seddeik Yasein, P. Agathoklis · 2006
In this paper, a technique for image normalization to deal with geometric distortions is proposed. The technique is based on transforming the image into a standard form with the objective to achieve invariance with respect to geometric distortions. The proposed technique relies on extracting some feature points from the image using a robust feature points extractor based on scale-interaction of Mexican-hat wavelets. The locations of such points are used to estimate the normalization parameters needed to normalize the image. Experimental results illustrate the accuracy of normalization and the robustness against several common image-processing operations.