DeepAI AI Chat
Log In Sign Up

Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selection

by   Yongchao Xu, et al.

Hierarchies, such as the tree of shapes, are popular representations for image simplification and segmentation thanks to their multiscale structures. Selecting meaningful level lines (boundaries of shapes) yields to simplify image while preserving intact salient structures. Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford-Shah functional. In this paper, we propose an efficient approach to hierarchical image simplification and segmentation based on the minimization of the piecewise-constant Mumford-Shah functional. This method conforms to the current trend that consists in producing hierarchical results rather than a unique partition. Contrary to classical approaches which compute optimal hierarchical segmentations from an input hierarchy of segmentations, we rely on the tree of shapes, a unique and well-defined representation equivalent to the image. Simply put, we compute for each level line of the image an attribute function that characterizes its persistence under the energy minimization. Then we stack the level lines from meaningless ones to salient ones through a saliency map based on extinction values defined on the tree-based shape space. Qualitative illustrations and quantitative evaluation on Weizmann segmentation evaluation database demonstrate the state-of-the-art performance of our method.


page 8

page 10


A Proof of the Tree of Shapes in n-D

In this paper, we prove that the self-dual morphological hierarchical st...

On the Role of Contrast and Regularity in Perceptual Boundary Saliency

Mathematical Morphology proposes to extract shapes from images as connec...

Prior-based Hierarchical Segmentation Highlighting Structures of Interest

Image segmentation is the process of partitioning an image into a set of...

Piecewise Linear Patch Reconstruction for Segmentation and Description of Non-smooth Image Structures

In this paper, we propose a unified energy minimization model for the se...

Segmentation hiérarchique faiblement supervisée

Image segmentation is the process of partitioning an image into a set of...

A Deep Learning Driven Active Framework for Segmentation of Large 3D Shape Collections

High-level shape understanding and technique evaluation on large reposit...

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

For the task of mobility analysis of 3D shapes, we propose joint analysi...