A new approach for image segmentation based on diffeomorphic registration and gradient fields
By: Junchao Zhou
Potential Business Impact:
Finds object edges in pictures without lots of examples.
Image segmentation is a fundamental task in computer vision aimed at delineating object boundaries within images. Traditional approaches, such as edge detection and variational methods, have been widely explored, while recent advances in deep learning have shown promising results but often require extensive training data. In this work, we propose a novel variational framework for 2D image segmentation that integrates concepts from shape analysis and diffeomorphic transformations. Our method models segmentation as the deformation of a template curve via a diffeomorphic transformation of the image domain, using the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework. The curve evolution is guided by a loss function that compares the deformed curve to the image gradient field, formulated through the varifold representation of geometric shapes. The approach is implemented in Python with GPU acceleration using the PyKeops library. This framework allows for accurate segmentation with a flexible and theoretically grounded methodology that does not rely on large datasets.
Similar Papers
Ideal Registration? Segmentation is All You Need
CV and Pattern Recognition
Makes medical scans match up better, even with movement.
NimbleReg: A light-weight deep-learning framework for diffeomorphic image registration
CV and Pattern Recognition
Aligns medical scans using simple shapes.
Implicit Deformable Medical Image Registration with Learnable Kernels
CV and Pattern Recognition
Makes medical scans match up perfectly for treatment.