Post Processing of image segmentation using Conditional Random Fields

TL;DR

This paper investigates the use of various Conditional Random Fields to improve the clarity of image segmentation results, especially for low-quality satellite images, through empirical evaluation on different datasets.

Contribution

It systematically evaluates different CRFs to identify the most effective approach for enhancing segmentation clarity in satellite and aerial imagery.

Findings

Certain CRFs outperform others on low-quality satellite images.

The approach improves segmentation clarity compared to baseline methods.

Different datasets reveal the strengths and limitations of various CRFs.

Abstract

The output of image the segmentation process is usually not very clear due to low quality features of Satellite images. The purpose of this study is to find a suitable Conditional Random Field (CRF) to achieve better clarity in a segmented image. We started with different types of CRFs and studied them as to why they are or are not suitable for our purpose. We evaluated our approach on two different datasets - Satellite imagery having low quality features and high quality Aerial photographs. During the study we experimented with various CRFs to find which CRF gives the best results on images and compared our results on these datasets to show the pitfalls and potentials of different approaches.