Self-Configuring and Evolving Fuzzy Image Thresholding

TL;DR

This paper introduces SC-EFIS, an improved evolving fuzzy image segmentation system that automatically configures parameters and eliminates the need for ROI detection, enhancing practical applicability.

Contribution

The paper presents SC-EFIS, a self-configuring version of EFIS that overcomes prior limitations by auto-tuning parameters and removing ROI detection dependency.

Findings

SC-EFIS effectively auto-configures parameters using training data.

SC-EFIS does not require ROI detection for feature calculation.

Experimental results demonstrate improved segmentation performance.

Abstract

Every segmentation algorithm has parameters that need to be adjusted in order to achieve good results. Evolving fuzzy systems for adjustment of segmentation parameters have been proposed recently (Evolving fuzzy image segmentation -- EFIS [1]. However, similar to any other algorithm, EFIS too suffers from a few limitations when used in practice. As a major drawback, EFIS depends on detection of the object of interest for feature calculation, a task that is highly application-dependent. In this paper, a new version of EFIS is proposed to overcome these limitations. The new EFIS, called self-configuring EFIS (SC-EFIS), uses available training data to auto-configure the parameters that are fixed in EFIS. As well, the proposed SC-EFIS relies on a feature selection process that does not require the detection of a region of interest (ROI).