Abstract
The hypothesis verification stage of the traditional image processing approach, consisting of low, medium, and high level processing, will suffer if the set of low level features extracted are of poor quality. We investigate the optimisation of the feature extraction chain by using Genetic Algorithms. The fitness function is a performance measure which reflects the quality of an extracted set of features. We will present some results and compare them with a Hill-Climbing approach.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
M. Mirmehdi, P.L. Palmer, J. Kittler, and H. Dabis. Complex feedback strategies for object recognition. Submitted to IEEE Transcations in Image Processing, 1996.
M. Mirmehdi, P.L. Palmer, J. Kittler, and H. Dabis. Complex feedback strategies for hypothesis generation and verification. In Proceedings of the 7th British Machine Vision Conference, pages 123–132. BMVA Press, 1996.
P.L. Palmer, H. Dabis, and J. Kittler. A performance measure for boundary detection algorithms. CVGIP: Image Understanding, 63(3):476–494, 1996.
B. Draper, A. Hanson, and E. Riseman. Knowledge-directed vision: Control, learning and integration. Proceedings of the IEEE, 84(11):1625–1637, 1996.
M. Mirmehdi, P.L. Palmer, and J. Kittler. Framework for control of parameters of low-level processes in early vision. Submitted to ECIS Workshop on Computational Vision, 1995.
M. Mirmehdi, P.L. Palmer, J. Kittler, and H. Dabis. Hypothesis generation and verification using complex feedback strategies for object recognition. Technical report, University of Surrey VSSP-TR-2/96, 1996.
D. Goldberg. Genetic algorithms in search, optimization & machine learning. Addison-Wesley, 1989.
P. Andrey and P. Tarroux. Unsupervised image segmentation using a distributed genetic algorithm. Pattern Recognition, 27(5):659–673, 1994.
S.K. Pal, D. Bhandari, and M.K. Kundu. Genetic algorithms for optimal image enhancement. Pattern Recognition Letters, 15(3):261–271, 1994.
S. Bhandarkar, Y. Zhang, and W. Potter. An edge-detection technique using genetic algorithm-based optimization. Pattern Recognition, 27(9):1159–1180, 1994.
E. Lutton and P. Martinez. A genetic algorithm for the detection of 2d geometric primitives in images. In Proceedings of International Conference on Pattern Recognition, pages 526–528, 1994.
G. Roth and M. D. Levine. Geometric primitive extraction using a genetic algorithm. IEEE PAMI, 16(9):901–905, 1994.
H. Saito and M. Mori. Application of genetic algorithms to stereo matching of images. Pattern Recognition Letters, 16(8):815–821, 1995.
M. Mirmehdi, P.L. Palmer, and J. Kittler. Genetic optimisation of the image feature extraction process. Pattern Recognition Letters, 18(4):355–365, 1997.
W. K. Pratt. Digital Image Processing. Wiley and Sons, 1978.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mirmehdi, M., Palmer, P.L., Kittler, J. (1997). Optimising the complete image feature extraction chain. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63931-4_231
Download citation
DOI: https://doi.org/10.1007/3-540-63931-4_231
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63931-2
Online ISBN: 978-3-540-69670-4
eBook Packages: Springer Book Archive