Enforcing Point-wise Priors on Binary Segmentation
نویسندگان
چکیده
Non-negative point-wise priors such as saliency map, defocus field, foreground mask, object location window, and user given seeds, appear in many fundamental computer vision problems. These priors come in the form of confidence or probability values, and they are often incomplete, irregular, and noisy, which eventually makes the labelling task a challenge. Our goal is to extract image regions that are aligned on the object boundaries and also in accordance with the given point-wise priors. To this end, we define a graph Laplacian spectrum based cost function and embed it into a minimization framework. For a comprehensive understanding, we analyze five alternative formulations, and demonstrate that the robust function version produces consistently superior results.
منابع مشابه
Stochastic segmentation using Gibbs priors
In earlier work, a fast stochastic method for reconstructing a certain class of twodimensional binary images from projections using Gibbs priors was presented. In the present study, we introduce a stochastic segmentation of magnetic resonance gray-scale images of trabecular bone using Gibbs priors. We show some results as well as some post-processing that can be used to clean up segmentations o...
متن کاملGeometry in Active Learning for Binary and Multi-class Image Segmentation
We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in both background-foreground and multi-class segmentation tasks that work in 2D and 3D image volumes. To this end, we use smoothness priors not only to select voxels most in need of annotation but to guarantee that they lie on 2D planar patch, which m...
متن کاملInteractive Image Segmentation using Optimization with Statistical Priors
Interactive image segmentation is important and has widespread applications in computer vision, computer graphics and medical imaging. A recent work has shown that interactive figure ground segmentation can be achieved by computing a transparency image using an optimization framework, where user interactions are used to supply constraints for solving a quadratic cost function with a unique glob...
متن کاملGrouping with Bias
We present a graph partitioning method to integrate prior knowledge in data grouping. We consider priors represented by three types of constraints: unitary constraints on labelling of groups, partial a priori grouping information, external in uence on binary constraints. They are modelled as biases in the grouping process. We incorporate these biases into graph partitioning criteria. Computatio...
متن کاملA Classification-Segmentation Framework for the Detection of Individual Trees in Dense MMS Point Cloud Data Acquired in Urban Areas
In this paper, we present a novel framework for detecting individual trees in densely sampled 3D point cloud data acquired in urban areas. Given a 3D point cloud, the objective is to assign point-wise labels that are both class-aware and instance-aware, a task that is known as instance-level segmentation. To achieve this, our framework addresses two successive steps. The first step of our frame...
متن کامل