Accès chercheur

EEDIS Laboratory

Evolutionary Engineering

and

Distributed Information Systems

Réseaux et Communication

Sécurité et Multimédia

Ingénierie des Connaissances

Data Mining & Web Intelligent

Interopérabilité des Systèmes d’information
& Bases de données

Développement Orienté Service

Pollen Detection in Images using Genetic Algorithms and Tabu Search


Auteurs:	» Menad Hanane » BEN-NAOUM Farah » Abdelmalek Amine
Type :	Revue Internationale
Nom du journal :	International Journal of Social Ecology and Sustainable Development (IJSESD) ISSN: 1947-8402
Volume : 13	Issue: 1	Pages: article 21
Lien : » https://www.igi-global.com/article/pollen-detection-in-images-using-genetic-algorithms-and-tabu-search/287877
Publié le :	02-09-2021

Pollen recognition is one of the most active research areas in field of ecological modeling. It is done

either via microscopic image analysis of pollen grains or via chemical components analysis. In this

paper, the authors were interested in pollen images analysis, in which they proposed an approach for

image segmentation in order to detect pollen grains in the microscopic images. The approach starts

by generating two pixels using genetic algorithms where one pixel of the selected ones is a pollen

pixel while the other is background pixels. Then the authors used k-means algorithm for image pixels

clustering to segment the input image. After that they classified the segmented images using machine

learning technics, and finally, they used taboo search to save the best pixels chosen by genetic algorithm

based on the obtained accuracy as fitness function. The obtained results proved the efficiency of the

proposed system where it could recognize 96.4% of the pollen grains.