Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, India

Research Article

Fuzzy Particle Swarm Optimization for Multilevel Thresholding in Image Segmentation and its Performance Evaluation with PSO

Download327 downloads
  • @INPROCEEDINGS{10.4108/eai.7-12-2021.2314753,
        author={Sridevi  B and Thambiraj  N and Chitra  M},
        title={Fuzzy Particle Swarm Optimization for Multilevel Thresholding in Image Segmentation and its Performance Evaluation with PSO},
        proceedings={Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, India},
        publisher={EAI},
        proceedings_a={ICCAP},
        year={2021},
        month={12},
        keywords={fuzzy pso performance},
        doi={10.4108/eai.7-12-2021.2314753}
    }
    
  • Sridevi B
    Thambiraj N
    Chitra M
    Year: 2021
    Fuzzy Particle Swarm Optimization for Multilevel Thresholding in Image Segmentation and its Performance Evaluation with PSO
    ICCAP
    EAI
    DOI: 10.4108/eai.7-12-2021.2314753
Sridevi B1,*, Thambiraj N2, Chitra M1
  • 1: PSG College of Technology
  • 2: PSG Polytechnic College
*Contact email: bsd.maths@psgtceh.ac.in

Abstract

In many applications of image processing, the gray levels of pixels belonging to an object are quite different from the gray levels of the pixels belonging to its background. The simplest property that pixels in a region can share is intensity. So, a natural way to segment such regions is through thresholding. This paper aims to determine the optimal threshold value using fuzzy systems in particle swarm optimization (PSO) algorithm. The proposed technique satisfies the objective function for Otsu method by maximizing between-class variance and also it overcomes the limitation of PSO. The efficiency and the stability of the algorithm is confirmed with few benchmark images.