Fageot, JulienUhlmann, VirginiePuespoeki, ZsuzsannaBeck, BenjaminUnser, MichaelDepeursinge, Adrien2021-05-222021-05-222021-05-222021-01-0110.1109/TIP.2021.3072499https://infoscience.epfl.ch/handle/20.500.14299/178267WOS:000641964400009We 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.Computer Science, Artificial IntelligenceEngineering, Electrical & ElectronicComputer ScienceEngineeringdetectorssignal to noise ratiosplines (mathematics)estimationpipelinescomputational modelingbiomedical imagingsteerable filterspattern detectionorientation estimationsnr criterionisotropic self-similar gaussian modelradial b-spinessplinestext::journal::journal article::research article