The Journal of the Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회논문지)

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지

A Novel Multi-focus Image Fusion Scheme using Nested Genetic Algorithms with "Gifted Genes"

재능 유전인자를 갖는 네스티드 유전자 알고리듬을 이용한 새로운 다중 초점 이미지 융합 기법

  • Received : 2008.12.29
  • Published : 2009.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

We propose in this paper a novel approach to image fusion in which the fusion rule is guided by optimizing an image clarity function. A Genetic Algorithm is used to stochastically select, comparative to the clarity function, the optimum block from among the source images. A novel nested Genetic Algorithm with gifted individuals found through bombardment of genes by the mutation operator is designed and implemented. Convergence of the algorithm is analytically and empirically examined and statistically compared (MANOVA) with the canonical GA using 3 test functions commonly used in the GA literature. The resulting GA is invariant to parameters and population size, and a minimal size of 20 individuals is found to be sufficient in the tests. In the fusion application, each individual in the population is a finite sequence of discrete values that represent input blocks. Performance of the proposed technique applied to image fusion experiments, is characterized in terms of Mutual Information (MI) as the output quality measure. The method is tested with C=2 input images. The results of the proposed scheme indicate a practical and attractive alternative to current multi-focus image fusion techniques.

본 논문에서 이미지 선명도 함수의 최적화에 의해 융합 법칙이 유도되는 새로운 이미지 융합 접근법을 제안한다. 선명도 함수에 비교하여 소스 이미지로부터 최적 블록을 통계적으로 선택하기 위하여 유전자 알고리듬이 사용되었다. 변이 연산에 의해 만들어진 유전인자들의 포격을 통해서 찾아진 재능 유전 인자를 갖는 새로운 네스티드 유전자 알고리듬을 설계하였고 구현하였다. 알고리듬의 수렴은 해석적으로, 실험적으로 그리고 통계적으로 3개의 테스트 함수를 사용하여 표준 GA와 비교하였다. 결과의 GA는 변수와 집단 크기에 불변이며, 최소 20 개체이면 시험에 충분하다는 것을 알 수 있었다. 융합 응용에서 모집단내의 각 개체는 입력 블록을 나타내는 유한한 이산 값을 갖는 개체이다. 이미지 융합 실험에 제안한 기법의 성능은 출력 품질 척도로 상호 정보량(MI)으로 특징지워진다. 제안한 방법은 C=2 입력 이미지에 대해 테스트되었다. 제안한 방법의 실험 결과는 현재의 다중 초점 이미지 융합 기법에 대한 실제적이고 매력적인 대안이 됨을 보여준다.

Keywords

References

  1. Nikolov, S. G., Lewis, J.J., O''Callaghan, R.J., Bull, D.R., and Canagarajah, C.N., "Hybrid Fused Displays: Between Pixel and Region-based Image Fusion", Proc 7th Int''l Conf. on Info. Fusion, pp. 1072-1079, Stockholm, Sweden, June 2004.
  2. Rajagopalan, A.N., Rao, K.S., and Kumar, Y.A., "Face Recognition Using Multiple Facial Features", ICVGIP 2004, volume 28, Issue 3 , pp. 335-341, 1 February 2007.
  3. Raskar, R., Ilie, A., and Yu, J., "Image Fusion for Context Enhancement", Proc 3rd Int''l Symposium on Non-Photorealistic Animation and Rendering (NPAR) , Annecy, France, 2004.
  4. Rockinger, O. "Pixel-Level Fusion of Image Sequences Using Wavelet Frames", Proc 16th Leeds Applied Share Research Workshop, Leeds University Press, 1996.
  5. Sadjadi, F., ""Comparative Image Fusion Analysis"", CVPRW'05 -- Workshops, pp.8, 2005
  6. Kingsbury, N., "The Dual-Tree Complex Wavelet Transform: A New Efficient Tool for Image Restoration and Enhancement", Proc IEE Digital Signal Processing Workshop, volume 86, 1998.
  7. Hill, P., Bull, D., and Canagarajah, C.N., "Image Fusion Using Complex Wavelets", Electronic Proceedings of the 13th British Machine Vision Conference ,pp 487-496, September 2002.
  8. Zhang, Z., and Blum, R., "Multisensor Image Fusion Using a Region-Based Wavelet Transform Approach", Proc DARPA IUW , pp 1447-1451, 1997
  9. Li, S., Kwok, J.T., and Wang, Y., "Multifocus Image Fusion Using Artificial Neural Networks", Pattern Recognition Letters, volume 23, pp 985-997, June 2002. https://doi.org/10.1016/S0167-8655(02)00029-6
  10. Huang, W., and Jhing, Z. "Multi-focus Image Fusion Using Pulse-Coupled Neural Networks", Pattern Recognition Letters, volume 28, Issue 9, pp 1123-1132, 1 July 2007 https://doi.org/10.1016/j.patrec.2007.01.013
  11. Wang, Z., and Ma, Y., "Medical Image Fusion Using PCNN", Information Fusion, volume 9, Issue 2, pp. 176-185, April 2008. https://doi.org/10.1016/j.inffus.2007.04.003
  12. Wan, T., Tzagkarakis, G., Tsakalides, P., Canagarajah, N., and Achim, A., "Context Enhancement Through Image Fusion: A Multiresolution Approach Based on Convolution of Cauchy Distributions," in Proc. 2008 International Conference on Acoustics, Speech, and Signal Processing (ICASSP '08), Las Vegas, NV, USA, March 30 - April 4, 2008.
  13. Cao, J., Spooner, D.P., Jarvis, S.A., Saini, S., and Nudd, G.R., "Agent-Based Grid Load Balancing Using Performance-Driven Task Scheduling", Proc 17th IEEE IPDPS, Nice, France, 2003
  14. Wall, Matthew, "A Genetic Algorithm for Resource-Constrained Scheduling". Massachusetts Institute of Technology, 1996
  15. Abdul, M. and Boggess, G., ""The Application of Genetic Algorithms to the Scheduling of Engineering Units"". Mississippi State University, 1997.
  16. Meijer, M., "Scheduling Parallel Processes Using Genetic Algorithms", Master Thesis in the field of Artificial Intelligence, section Autonomous Systems 2004 [online], Available from: http://www.science.uva.nl/research/pscs/papers/archive/Meijer2004a.pdf
  17. Burt, P,J., and Kolczynski, R.J., "Enhanced image capture through fusion", Proc. 4th Inti. Confon Comp Vision, pp.173-182, 1993.
  18. Li, H., Maniunath, B. S., and Mitra, S. K., "Multisensor image fusion using the wavelet transform", Graphical Models and Image Processing, 57:235-245, 1995. https://doi.org/10.1006/gmip.1995.1022
  19. Jackson, W.C., and Norgard, J.D., "A Hybrid Genetic Algorithm with Blotzmann Convergence Properties", Journal of optimization Theory and Applications, 136:431-443, 2008. https://doi.org/10.1007/s10957-007-9308-8
  20. Spears, W., and DeJong, K., "An Analysis of Multi-point Crossover", Rawlins, G,J. E.,editor,. Morgan Kauffman, pp.301-315.
  21. Whitley, D., "A Genetic Algorithm Tutorial", Tech. Rep. CS-93-103. DCS, Col State Univ, Fort Collins, CO8052 ,March 1993.
  22. Chen, J. H, "Theoretical Analysis of Multi-Objective GA Algorithms - Convergence Time, Pop Sizing, and Disequilibrium", Tech. Rep. for IEEE NNS Walter Karplus Research Grant[online], Available from:http://ieee-cis.org/_files/EAC_Research_2003_Report_Chen.pdf
  23. Rudolph. G., "Convergence Analysis of Canonical Genetic Algorithms", IEEE Trans. on Neural Networks: Special Issue on EC, vol.5:1, pp. 96-101, 1994 https://doi.org/10.1109/72.265964