Decoupled Active Surface for Volumetric Image Segmentation

Finding the surface of a volumetric 3D object is a fundamental problem in computer vision. Energy minimizing splines, such as active surfaces, have been used to carry out such tasks, evolving under the influence of internal and external energies until the model converges to a desired surface. The present deformable model based surface extraction techniques are computationally expensive and are generally unreliable in identifying the surfaces of noisy, high-curvature and cluttered 3D objects. This paper proposes a novel decoupled active surface (DAS) for identifying the surface of volumetric 3D objects. The proposed DAS introduces two novel aspects which leads to robust, efficient and accurate convergence. First, rather than a parameterized surface, which leads to difficulties with complex shapes and parameter singularities, the DAS uses a conforming triangular mesh to represent the surface. Second, motivated by earlier successes in two-dimensional segmentation, the DAS treats the two energy components separately and uses novel solution techniques to efficiently minimize the two energy terms separately. The performance of DAS in segmenting static 3D objects is presented using several natural and synthetic volumetric images, with excellent convergence results.