Sayısal Holografide İkili Kodlu Genetik Algoritma ve Faz Düzeltme Kullanarak Görüntünün Yeniden Oluşturulmasının İncelenmesi

Öz

Görüntü işlemede, görüntünün yeniden oluşturulması temel bir işlemdir ve görüntülerin mümkün olan en düşük gürültü ve en yüksek doğrulukla yeniden oluşturulması istenir. Sayısal holografi, yaygın olarak Hızlı Fourier Dönüşümünü (FFT) kullanan görüntü yeniden oluşturma yöntemlerinden biridir. Ancak, sayısal holografinin yeniden oluşturma sürecinde gürültüyü azaltmak veya sayısal hologramı optimize etmek için genetik algoritma (GA) gibi çeşitli yinelemeli yöntemler kullanılabilir. Bu çalışmada, sayısal holografide ikili kodlu genetik algoritma (BGA) kullanılarak gerçekleştirilen bir görüntü yeniden oluşturma sunulmaktadır. Bu amaçla, camdan yapılmış bir yıldız nesnenin görüntüsü hem orjinal olarak hem de orijinal olarak yeniden yapılandırılana benzer bir çözüm bulmak için BGA kullanılarak yeniden oluşturulmaktadır. Ayrıca yeniden oluşturulan görüntüdeki faz düzeltme etkisi Goldenstein ve Quality guided path teknikleri olmak üzere iki farklı yöntem kullanılarak değerlendirilmektedir. Elde edilen sonuçlar, BGA'nın orijinal olarak yeniden oluşturulan görüntüye oldukça benzer bir çözüm sağladığından, sayısal holografide yaygın olarak kullanılan yeniden oluşturma işlemine bir alternatif olarak düşünülebileceğini göstermektedir. Ayrıca, faz bilgisine sahip 3 boyutlu (3D) görüntü, faz düzeltme teknikleri ile elde edildiğinden, daha kaliteli görüntülere sahip olunmasını sağlar.

Anahtar Kelimeler

• Sayısal holografi
• görüntü yeniden oluşturma
• ikili kodlu genetik algoritma
• faz düzeltme.

Evaluation of Image Reconstruction Using Binary Genetic Algorithm and Unwrapping in Digital Holography

Öz

Image reconstruction is a fundamental task of image processing and images are desired to be reconstructed with the lowest noise and most accuracy possible. Digital holography is one of the methods for image reconstruction that uses Fast Fourier Transform (FFT) as a commonly tool. However, several iterative methods such as genetic algorithm (GA) can be used to decrease the noise or optimize the digital hologram in the reconstuction process for digital holography. In this paper, we propose an image reconstruction task that is performed by using binary genetic algorithm (BGA) in digital holography. In this scheme, the image of a glass made star object is reconstructed both orginally and also by using BGA to find a similar solution to the originally reconstructed one. In addition, unwrapping effect in the reconstructed image is evaluated by using two different methods that are Goldenstein's and Quality guided path following techniques. The obtained results indicate that since BGA provides a solution with higher similarity to the originally reconstructed one, it can be considered as an alternative to common reconstruction process in digital holography. In addition, since 3-dimensional (3D) image with phase information is obtained by unwrapping techniques, it provides to have better quality images.

Anahtar Kelimeler

• Digital holography
• image reconstruction
• binary genetic algorithm
• unwrapping

Kaynakça

1. Hansen, M. S.,Kellman, P., Image Reconstruction: An Overview for Clinicians, Journal of Magnetic Resonance Imaging, 2015, 41(3):573-585.
2. Moon, I.,Jaferzadeh, K., Automated Digital Holographic Image Reconstruction with Deep Convolutional Neural Networks, Proc. SPIE 11402, Three-Dimensional Imaging, Visualization, and Display, 2020, 114020A.
3. Kugler, M.,Goto, Y., Tamura, Y., Kawamura, N., Kobayashi, H., Yokota, T., Iwamoto, C., Ohuchida, K., Hashizume, M., Shimizu, A., and Hontani, H., Robust 3D Image Reconstruction of Pancreatic Cancer Tumors From Histopathological Images with Different Stains and Its Quantitative Performance Evaluation, International Journal for Computer Assisted Radiology and Surgery, 2019,14(12):2047-2055.
4. Kawamura, N.,Yokota, T., Hontani, H., Sakata, M., and Kimura, Y., Parametric PET Image Reconstruction Viaregional Spatial Bases and Pharmacokinetic Time Activity Model, Entropy, 2017, 19(629):1-20.
5. Rusdi, N. A.,Yahya, Z. R., Roslan, N.,and Azman Wan Muhamad, W. Z., Reconstruction of Medical Images Using Artificial Bee Colony Algorithm, Mathematical Problems in Engineering, 2018, 2018: 1-7.
6. S.,Mirjalili, J., Song Dong, A. S., Sadiq, and H., Faris, Genetic Algorithm: Theory, Literature Review, and Application in Image Reconstruction, In: Mirjalili S., Song Dong J., Lewis A. (eds) Nature-Inspired Optimizers. Studies in Computational Intelligence, 811, Springer, Cham, 2020.
7. Türken, T., Pala, T., Modeling and Optimization of Sour Cherry Juice Antioxidant Activity by Using Response Surface Methodology and Genetic Algorithm, El-Cezeri Journal of Science and Engineering,2016, 3(2): 238-247.
8. Li, X., Jiang, T., and Evans, D. J., Medical Image Reconstruction Using a Multi-Objective Genetic Local Search Algorithm, International Journal of Computer Mathematics,2000,74(3):301-314.

9. Qureshi, S. A.,Mirza, S. M., and Arif, M., A Hybrid Continuous Genetic Algorithm for Parallel-Ray Transmission Tomography Image Reconstruction,Journal of Biomedical Informatics, 2006, 1-10.
10. Majeed, A., Mt Piah, A. R., Image Reconstruction Using Rational Ball Interpolant and Genetic Algorithm, Applied Mathematical Sciences, 2014, 8(74):3683-3692.
11. Gray, C. C., Al‑Maliki, S. F., and Vidal, F. P., Data Exploration in Evolutionary Reconstruction of PET Images, Genetic Programming and Evolvable Machines, 2018, 19: 391-419.
12. Bourgeat, B., Fripp, J., Stanwell, P., and Ramadan, S., MR Image Segmentation of the Knee Bone Using Phase Information,Medical Image Analysis,2007, 11(4): 325-335.
13. Bioucas-Dias, J. S.,Valadao, G., Phase Unwrapping: A New Max-flow/min-cut Based Approach, IEEE International Conference on Image Processing, 2005, 1-4.
14. Abdul-Rahman, H. S., Gdeisat, M. A., Burton, D. R., Lalor, M. J., Lilley, F., and Moore, C. J., Fast and Robust Three-dimensional Best Path Phase Unwrapping Algorithm,Applied Optics,2007,46(26): 6623-6635.
15. Hubig, M., Suchandt, S., and Adam, N., A Class of Solution-invariant Transformations of Cost Functions for Minimum Cost Flow Phase Unwrapping,Journal of the Optical Society of America,2004,21(10): 1975-87.
16. Su, X., Chen, W., Reliability-guided Phase Unwrapping Algorithm: A Review, Optics and Lasers in Engineering, 2004,42(3): 245-61.
17. Diane, N. H., Kim, M. A., Teitell, J. R., and Zangle, T. A., Hybrid Random Walk-linear Discriminant Analysis Method for Unwrapping Quantitative Phase Microscopy Images of Biological Samples,Journal of Biomedical Optics,2015,20(11): 111211.
18. Zappa, E., Busca, G., Comparison of Eight Unwrapping Algorithms Applied to Fourier-Transform Profilometry,Optics and Lasers in Engineering,2008, 46(2): 106-116.
19. Wei, H.,Ling, X., andFeng, L., Sparse-representation-based Direct Minimum 𝐿𝑝-norm Algorithm for MRI Phase Unwrapping, Computational and Mathematical Methods in Medicine, 2014, 2014: 1-11.
20. Z.,Michalewicz, Genetic Algorithms + Data Structure= Evolution Programs, AI Series Springer-Verlag, 1994.
21. D. E.,Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, Reading, Mass, 1989.
22. M.,Mitchell, An Introduction to Genetic Algorithms, MIT Press, Cambridge, MA, 1996.
23. Abdul-Rahman, H. S., Gdeisat, M. A., Burton, D. R., and Lalor, M. J., Three Dimensional Phase Unwrapping Algorithms: A Comparison,Proceedings of Photon06 Conference, 2006, 1-12.
24. D. C.,Ghiglia, M. D., Pritt,Two-Dimensional Phase Unwrapping, Wiley, 1998.
25. Ghiglia, D. C., Mastin, G. A., and Romero, L. A., Cellular Automata Method for Phase Unwrapping,Journal of the Optical Society of America, 1987, 4(1): 267-80.
26. Goldstein, R. M., Zebker, H. A., and Werner, C. L., Satellite Radar Interferometry: Two-Dimensional Phase Unwrapping, Radio Science, 1988,23(4): 713-20.
27. Pellizzari, C. J., Phase Unwrapping in the Presence of Strong Turbulence, Master of Science, Air Force Institute of Technology Air University, 2010. Onur, T.O., Ustabas Kaya, G., and Kaya, C., Phase Shifted-Lateral Shearing Digital Holographic Microscopy Imaging for Early Diagnosis of Cysts in Soft Tissue-Mimicking Phantom,Applied PhysicsB, 2021,127(61): 1-13.
28. Sara, U., Akter, M., and Uddin, M., Image Quality Assessment Through FSIM, SSIM, MSE and PSNR—A Comparative Study, Journal of Computer and Communications, 2019,7(3): 8-18.