Genetic Programming for Object Detection : a Two-Phase Approach with an Improved Fitness Function
Zhang, Mengjie (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science)
Bhowan, Urvesh (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science)
Ny, Bunna (Victoria University of Wellington (Wellington, Nova Zelanda). School of Mathematics, Statistics and Computer Science)

Data:	2007
Resum:	This paper describes two innovations that improve the efficiency and effectiveness of a genetic programming approach to object detection problems. The approach uses genetic programming to construct object detection programs that are applied, in a moving window fashion, to the large images to locate the objects of interest. The first innovation is to break the GP search into two phases with the first phase applied to a selected subset of the training data, and a simplified fitness function. The second phase is initialised with the programs from the first phase, and uses the full set of training data with a complete fitness function to construct the final detection programs. The second innovation is to add a program size component to the fitness function. This approach is examined and compared with a neural network approach on three object detection problems of increasing difficulty. The results suggest that the innovations increase both the effectiveness and the efficiency of the genetic programming search, and also that the genetic programming approach outperforms a neural network approach for the most difficult data set in terms of the object detection accuracy.
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	Artificial Intelligence approaches to Computer Vision Object Recognition ; Image Analysis ; Genetic Programming ; Neural Networks ; Apropament de la Intel·ligència artificial a la visió per computadora ; Reconeixement objecte ; Anàlisi d'imatge ; Programació genètica ; Xarxa neural ; Acercamiento de la Inteligencia artificial en la visión por computadora ; Reconocimiento objeto ; Análisis de imagen ; Programación genética ; Red neural
Publicat a:	ELCVIA : Electronic Letters on Computer Vision and Image Analysis, V. 6 n. 1 (2007) p. 27-43, ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.es/article/view/v6-n1-zhang-bhowan
Adreça alternativa: https://raco.cat/index.php/ELCVIA/article/view/85557
DOI: 10.5565/rev/elcvia.135

17 p, 263.4 KB

El registre apareix a les col·leccions:
Articles > Articles publicats > ELCVIA
Articles > Articles de recerca