Image Thresholding Using TRIBES, a Parameter-Free Particle Swarm Optimization Algorithm

Authors:
Yann Cooren;Amir Nakib;Patrick Siarry
Affiliations:
Laboratoire Images, Signaux et Systèmes Intelligents, LiSSi, E.A 3956, Université de Paris 12, Créteil, France 94010;Laboratoire Images, Signaux et Systèmes Intelligents, LiSSi, E.A 3956, Université de Paris 12, Créteil, France 94010;Laboratoire Images, Signaux et Systèmes Intelligents, LiSSi, E.A 3956, Université de Paris 12, Créteil, France 94010
Venue:
Learning and Intelligent Optimization
Year:
2008

Citing 8
Cited 0

Digital image processing (2nd ed.)

Digital image processing (2nd ed.)
A survey of thresholding techniques

Computer Vision, Graphics, and Image Processing
Optimal thresholding—a new approach

Pattern Recognition Letters
Optimal multi-thresholding using a hybrid optimization approach

Pattern Recognition Letters
Understanding UMTS Radio Network Modelling, Planning and Automated Optimisation: Theory and Practice

Understanding UMTS Radio Network Modelling, Planning and Automated Optimisation: Theory and Practice
Image histogram thresholding based on multiobjective optimization

Signal Processing
Magnetic resonance image segmentation based on two-dimensional exponential entropy and a parameter free PSO

EA'07 Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution
The particle swarm - explosion, stability, and convergence in amultidimensional complex space

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Finding the optimal threshold(s) for an image with a multimodal histogram is described in classical literature as a problem of fitting a sum of Gaussians to the histogram. The fitting problem has been shown experimentally to be a nonlinear minimization problem with local minima. In this paper, we propose to reduce the complexity of the method, by using a parameter-free particle swarm optimization algorithm, called TRIBES which avoids the initialization problem. It was proved efficient to solve nonlinear and continuous optimization problems. This algorithm is used as a "black-box" system and does not need any fitting, thus inducing time gain.