Cargando…

Object Detection Based on Template Matching through Use of Best-So-Far ABC

Best-so-far ABC is a modified version of the artificial bee colony (ABC) algorithm used for optimization tasks. This algorithm is one of the swarm intelligence (SI) algorithms proposed in recent literature, in which the results demonstrated that the best-so-far ABC can produce higher quality solutio...

Descripción completa

Detalles Bibliográficos
Autores principales: Banharnsakun, Anan, Tanathong, Supannee
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2014
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4000638/
https://www.ncbi.nlm.nih.gov/pubmed/24812556
http://dx.doi.org/10.1155/2014/919406
Descripción
Sumario:Best-so-far ABC is a modified version of the artificial bee colony (ABC) algorithm used for optimization tasks. This algorithm is one of the swarm intelligence (SI) algorithms proposed in recent literature, in which the results demonstrated that the best-so-far ABC can produce higher quality solutions with faster convergence than either the ordinary ABC or the current state-of-the-art ABC-based algorithm. In this work, we aim to apply the best-so-far ABC-based approach for object detection based on template matching by using the difference between the RGB level histograms corresponding to the target object and the template object as the objective function. Results confirm that the proposed method was successful in both detecting objects and optimizing the time used to reach the solution.