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

TL;DR

This paper introduces a unified energy minimization framework for segmenting non-smooth image structures that simultaneously produces a dictionary of descriptors, demonstrating superior performance over existing methods.

Contribution

It presents a novel joint segmentation and description model based on piecewise linear patch reconstruction, with theoretical error bounds and practical validation.

Findings

Proves segmentation error is bounded by the energy functional.

Achieves superior segmentation of various textures compared to related methods.

Capable of handling both smooth and non-smooth structures with a unified approach.

Abstract

In this paper, we propose a unified energy minimization model for the segmentation of non-smooth image structures. The energy of piecewise linear patch reconstruction is considered as an objective measure of the quality of the segmentation of non-smooth structures. The segmentation is achieved by minimizing the single energy without any separate process of feature extraction. We also prove that the error of segmentation is bounded by the proposed energy functional, meaning that minimizing the proposed energy leads to reducing the error of segmentation. As a by-product, our method produces a dictionary of optimized orthonormal descriptors for each segmented region. The unique feature of our method is that it achieves the simultaneous segmentation and description for non-smooth image structures under the same optimization framework. The experiments validate our theoretical claims and show the clear superior performance of our methods over other related methods for segmentation of various image textures. We show that our model can be coupled with the piecewise smooth model to handle both smooth and non-smooth structures, and we demonstrate that the proposed model is capable of coping with multiple different regions through the one-against-all strategy.