Abstract

Image segmentation is a fundamental problem in Image Pro- cessing, Computer Vision and Medical Imaging with numerous applica- tions. In this paper, we address the atlas-based image segmentation prob- lem which involves registration of the atlas to the sub ject or target image in order to achieve the segmentation of the target image. Thus, the tar- get image is segmented with the assistance of a registration process. We present a novel variational formulation of this registration assisted image segmentation problem which leads to solving a coupled set of nonlinear PDEs that are solved using eficient numerical schemes. Our work is a departure from earlier methods in that we have a unified variational prin- ciple wherein registration and segmentation are simultaneously achieved. We present several 2D examples on synthetic and real data sets along with quantitative accuracy estimates of the registration.