Subpixel object segmentation using wavelets and multiresolution analysis

Ray Sheombarsing, Nikita Moriakov, Jan-jakob Sonke, Jonas Teuwen

Keywords: Segmentation, wavelets, contour prediction, multiresolution analysis

Abstract: We propose a novel deep learning framework for fast prediction of boundaries of two-dimensional simply connected domains using wavelets and Multiresolution Analysis (MRA). The boundaries are modelled as (piecewise) smooth closed curves using wavelets and the so-called Pyramid Algorithm. Our network architecture is a hybrid analog of the U-Net, where the down-sampling path is a two-dimensional encoder with learnable filters, and the upsampling path is a one-dimensional decoder, which builds curves up from low to high resolution levels. Any wavelet basis induced by a MRA can be used. This flexibility allows for incorporation of priors on the smoothness of curves. The effectiveness of the proposed method is demonstrated by delineating boundaries of simply connected domains (organs) in medical images using Debauches wavelets and comparing performance with a U-Net baseline. Our model demonstrates up to 5x faster inference speed compared to the U-Net, while maintaining similar performance in terms of Dice score and Hausdorff distance.

One-sentence Summary: In this paper a novel deep learning framework for fast prediction of contours is developed using wavelets and multiresolution analysis.