Principled Design and Implementation of Steerable Detectors
J. Fageot, V. Uhlmann, Z. Püspöki, B. Beck, M. Unser, A. Depeursinge
IEEE Transactions on Image Processing, vol. 30, pp. 4465-4478, 2021.
We provide a complete pipeline for the detection of patterns of interest in an image. In our approach, the patterns are assumed to be adequately modeled by a known template, and are located at unknown positions and orientations that we aim at retrieving. We propose a continuous-domain additive image model, where the analyzed image is the sum of the patterns to localize and a background with self-similar isotropic power-spectrum. We are then able to compute the optimal filter fulfilling the SNR criterion based on one single template and background pair: it strongly responds to the template while being optimally decoupled from the background model. In addition, we constrain our filter to be steerable, which allows for a fast template detection together with orientation estimation. In practice, the implementation requires to discretize a continuous-domain formulation on polar grids, which is performed using quadratic radial B-splines. We demonstrate the practical usefulness of our method on a variety of template approximation and pattern detection experiments. We show that the detection performance drastically improves when we exploit the statistics of the background via its power-spectrum decay, which we refer to as spectral-shaping. The proposed scheme outperforms state-of-the-art steerable methods by up to 50% of absolute detection performance.
@ARTICLE(http://bigwww.epfl.ch/publications/fageot2101.html, AUTHOR="Fageot, J. and Uhlmann, V. and P{\"{u}}sp{\"{o}}ki, Z. and Beck, B. and Unser, M. and Depeursinge, A.", TITLE="Principled Design and Implementation of Steerable Detectors", JOURNAL="{IEEE} Transactions on Image Processing", YEAR="2021", volume="30", number="", pages="4465--4478", month="", note="")