Image Registration Based on Improved Ant Colony Algorithm

Abstract:

Image registration is an important technology in image processing and computer vision, ant colony algorithm search for the optimal registration parameters in image registration has a strong global optimization ability, but the final search to the accuracy of the registration parameters and search for a very long time. in this paper an improved ant colony algorithm is presented to improve the registration accuracy by the original ant colony algorithm and simplex algorithm has a strong local optimization, improved ant colony algorithm heuristic function in order to improve the convergence speed; Finally, the improved ant colony algorithm combined with multi-resolution registration strategy to reduce the time of image registration. The experimental results show that compared with the original ant colony algorithm, an improved ant colony algorithm can effectively improve the image registration accuracy, and can reduce the number of convergence of the algorithm.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 683-686
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.683
• Online since: September 2013
• Authors: Ying Tian, Hao Di Ma
• Keywords: Ant Colony Algorithm (ACA), Mage Registration, Mutual Information (MI), Simplex Algorithms

References

[1] Holden M, Hill D L G, Denton E R E, et al. Voxel similarity measures for 3D serial MR image registration[J]. IEEE Transactions on Medical Imaging, 2000, 19(2): 94-102.

DOI: 10.1109/42.836369

[2] West J, Fitzpatrick J M, Wang MY, ea al. Comparison and evaluation of retrospective intermodality registration techniques[J]. Journal of Computer Assisted Tomography, 1997, 21(4): 554-566.

[3] Colorni A, Dorigo M, Maniezzo V, et, al. Distributed optimization by ant colonies. Proceedings of the 1st European Conference on Artifical Life, 1991, 134-142.

[4] Dorigo M．Optimization learning and natural algorithms Ph D. Thesis Department of Electronics，Politecnico diMilano, Italy, (1992).

[5] Maes. F, Collignon A, Vandermeulen D, et, a1. Multimodality image registration by maximization of mutual information[J]. IEEE Transactions on Medical Imaging, 1997, 16(2): 187-198.

DOI: 10.1109/42.563664

[6] Daniel M，Martin M．Ant colony optimization with global pheromone evaluation for scheduling a single machine. Applied Intelligence, 2003, 18: 105-111.