3B Şekil Oluşturmak için Alt Örneklemesiz Shearlet Dönüşümüne Dayalı Yeni ve Yüksek Kaliteli Odaklama Ölçüm Operatörü

Öz

3B şekil oluşturulma sürecinde herhangi ek donanım gerektirmeyen Odaktan Şekil (Shape From Focus - SFF) en çok tercih edilen stratejilerdendir. SFF stratejisi, 3B şekil oluşturma sürecinde farklı odaklı 2B görüntü serisi kullanmakta ve üç temel aşamadan oluşmaktadır: (1) Farklı odaklı 2B görüntü serisinin elde edilmesi, (2) Görüntü piksellerinin odaklama değerlerinin hesaplanması ve (3) Maksimum odaklı pikselin seçilmesi. Yüksek doğruluk ve daha düşük gürültü ile 3B şekil oluşturmak için, araştırmacılar SFF'nin ikinci aşamasında yeni odaklama ölçüm operatörü önermek yerine genellikle bir ön veya son işlem algoritmaları geliştirmektedirler. Literatür çalışmalarının aksine, bu çalışmada herhangi bir ön veya son işlem gerektirmeyen Alt Örneklemesiz Shearlet Dönüşümü'ne dayalı yeni ve yüksek kaliteli odaklama ölçüm operatörü önerilmektedir. Önerilen odaklama ölçüm operatörünün etkinliği sentetik görüntü serileri kullanılarak pencere boyutu ve gürültü seviyesi gibi farklı koşullar altında analiz edilmektedir. Elde edilen öznel ve nesnel sonuçlar önerilen odaklama ölçüm operatörünün daha iyi performans sağladığını göstermektedir.

Anahtar Kelimeler

• Odaklama Ölçüm Operatörü
• Odaktan Şekil
• 3B Şekil Oluşturma
• Alt Örneklemesiz Shearlet Dönüşümü

A New High Quality Focus Measurement Operator Based on Nonsubsampled Shearlet Transform for 3D Shape Reconstruction

Öz

Shape From Focus (SFF), which does not require any additional hardware in the 3D shape creation process, is one of the most preferred strategies. The SFF strategy uses a series of 2D images with different focusing on the process of creating 3D shapes of objects and consists of three basic steps: (1) Obtaining a 2D image series with different focus, (2) Calculating the focus values of image pixels, and (3) Selection of maximum focused pixel. In order to create 3D shapes with high accuracy and lower noise, researchers often develop a pre- or post-processing algorithms instead of proposing new focus measurement operators in the second stage of SFF. In this study, a new and high-quality focusing measurement operator based on Nonsubsampled Shearlet Transform is proposed, which does not require any pre- or post-processing. Proposed focus measurement operator is analyzed under different conditions. Subjective and objective results show that the proposed focus measure operator achieves better performance

Anahtar Kelimeler

• Focus Measurement Operator
• Shape from Focus
• 3D Shape reconstruction
• Nonsubsampled Shearlet Transform

Kaynakça

1. B. Billiot, F. Cointault, L. Journaux, J.C. Simon, andP.Gouton “3D image acquisition system based onshape from focus technique”, Sensors, vol. 13, no. 4,pp. 5040-5053, 2013.
2. S.O. Shim, A.S. Malik, and T.S. Choi “Accurateshape from focus based on focus adjustment in opticalmicroscopy”, Microscopy research and technique,vol. 72, no. 5, pp. 362–370, 2009.
3. S. Pertuz, D. Puig, and M.A. Garcia “Analysis offocus measure operators for shape-from-focus”,Pattern Recognition, vol. 46, no. 5, pp. 1415–1432,2013.
4. A.S. Malik, and T.S Choi “A novel algorithm forestimation of depth map using image focus for 3dshape recovery in the presence of noise”, PatternRecognition, vol. 41, no. 7, pp. 2200–2225, 2008.
5. J.M. Geusebroek, F. Cornelissen, A.W. Smeulders,and H. Geerts “Robust autofocusing in microscopy”,Cytometry: The Journal of the International Societyfor Analytical Cytology, vol. 39, no. 1, pp. 1–9, 2000.
6. M.B. Ahmad, and T.S. Choi “Application of threedimensional shape from image focus in lcd/tftdisplays manufacturing”, IEEE Transactions onConsumer Electronics, vol. 53, no. 1, pp. 1–4, 2007.
7. S.K. Nayar “Shape from focus system”, ComputerVision and Pattern Recognition, Proceedings IEEEComputer Society Conference on. IEEE, pp. 302–308, 1992.
8. J.L. Pech Pacheco, G. Crist´obal, J. ChamorroMartinez, and J. Fern´andez Valdivia “Diatomautofocusing in brightfield microscopy: acomparative study”, Pattern Recognition, 15th International Conference on. IEEE, pp. 314–317, 2000.

9. Y. An, G. Kang, I.J. Kim, H.S. Chung, and J. Park“Shape from focus through laplacian using 3dwindow”, Future Generation Communication andNetworking, 2008 Second International Conferenceon. IEEE, pp. 46–50, 2008.
10. [10]A. Thelen, S. Frey, S. Hirsch, and P. Hering“Improvements in shape-from-focus for ographicreconstructions with regard to focus operators,neighborhood-size, and height value interpolation”,IEEE Transactions on Image Processing, vol. 18, no.1, pp. 151–157, 2009.
11. T. Yan, Z. Hu, Y. Qian, Z. Qiao, and L. Zhang “3dshape reconstruction from multifocus image fusionusing a multidirectional modified laplacian operator”,Pattern Recognition, vol. 98, p. 107065, 2020.
12. C.Y. Wee, and R. Paramesran “Measure of imagesharpness using eigenvalues”, Information Sciences,vol. 177, no. 12, pp. 2533–2552, 2007.
13. P.T. Yap, and P. Raveendran “Image focus measurebased on chebyshev moments”, IEE Proceedings-Vision, Image and Signal Processing, vol. 151, no.2,pp. 128–136, 2004.
14. S.Y. Lee, Y. Kumar, J.M. Cho, S.W. Lee, and S.W.Kim “Enhanced autofocus algorithm using robustfocus measure and fuzzy reasoning”, IEEETransactions on Circuits and Systems for VideoTechnology, vol. 18, no. 9, pp. 1237–1246, 2008.
15. C.H. Shen, and H.H. Chen “Robust focus measure forlow-contrast images”, Consumer Electronics,International Conference on. IEEE, pp. 69–70, 2006.
16. S.Y. Lee, J.T. Yoo, Y. Kumar, and S.W. Kim “Reduced energy-ratio measure for robust autofocusing in digital camera”, IEEE Signal Processing Letters, vol. 16, no. 2, pp. 133–136, 2009.
17. H. Xie, W. Rong, and L. Sun “Construction and evaluation of a wavelet-based focus measure for microscopy imaging”, Microscopy research and technique, vol. 70, no. 11, pp. 987–995, 2007.
18. U. Ali, and M.T. Mahmood “3d shape recovery by aggregating 3d wavelet transform-based image focus volumes through 3d weighted least squares”, Journal of Mathematical Imaging and Vision, pp. 1–19, 2019.
19. F.S. Helmli, and S. Scherer “Adaptive shape from focus with an error estimation in light microscopy”, Image and Signal Processing and Analysis, Proceedings of the 2nd International Symposium on. IEEE, pp. 188–193, 2001.
20. J. Lorenzo, M. Castrillon, J.M´endez, and O. Deniz “Exploring the use of local binary patterns as focus measure”, Computational Intelligence for Modelling Control and Automation, International Conference on. IEEE, pp. 855–860, 2008.
21. F. Mahmood, J. Mahmood, A. Zeb, and J. Iqbal “3d shape recovery from image focus using gabor features”, Machine Vision, Tenth International Conference on. IEEE, vol. 10696, pp. 106961F, 2018.
22. R. Minhas, A.A. Mohammed, and Q.J. Wu “Shape from focus using fast discrete curvelet transform”, Pattern Recognition, vol. 44, no. 4, pp. 839–853, 2011.
23. R. Minhas, A.A. Mohammed, Q.J. Wu, and M.A. Sid Ahmed “3d shape from focus and depth map computation using steerable filters”, Image Analysis and Recognition, International Conference on. IEEE, pp. 573–583, 2009.
24. H. Nanda, and R. Cutler “Practical calibrations for a real-time digital omnidirectional camera”, CVPR Technical Sketch vol. 20, no. 2, 2001.
25. M.V. Shirvaikar “An optimal measure for camera focus and exposure”, System Theory, Thirty-Sixth Southeastern Symposium on. IEEE, pp. 472– 475, 2004.
26. T. Fan, and H. Yu “A novel shape from focus method based on 3d steerable filters for improved performance on treating textureless region”, Optics Communications, vol. 410, pp. 254–261, 2018.
27. U. Ali, V. Pruks, and M.T. Mahmood “Image focus volume regularization for shape from focus through 3d weighted least squares”, Information Sciences, vol. 489, pp. 155–166, 2019.
28. M. Chen, Y. Zhong, Z. Li and J. Wu “A novel 3d shape reconstruction method based on maximum correntropy kalman filtering”, Sensor Review, 2018.
29. H.S. Jang, M.S. Muhammad and T.S. Choi “Optimal depth estimation using modified kalman filter in the presence of non-gaussian jitter noise”, Microscopy Research and Technique, pp. 1–8, 2018.
30. H.S. Jang, M.S. Muhammad and T.S. Choi “Bayes filter based jitter noise removal in shape recovery from image focus”, Journal of Imaging Science and Technology, vol. 63, no. 2, pp. 20501–1, 2019.
31. H.S. Jang, M.S. Muhammad and T.S. Choi “Optimizing image focus for shape from focus through locally weighted non-parametric regression”, IEEE Access, vol. 7, pp. 74393–74400, 2019.
32. H.S. Jang, M.S. Muhammad, G. Yun and D.H. Kim “Sampling based on kalman filter for shape from focus in the presence of noise”, Applied Sciences, vol. 9, no. 16, pp. 3276, 2019.
33. P.G. Kumar and R. Ranjan Sahay “Accurate structure recovery via weighted nuclear norm: A low rank approach to shape-from-focus”, Computer Vision, Proceedings of the IEEE International Conference on. IEEE, pp. 563–574, 2017.
34. I. Lee, M.T. Mahmood and T.S. Choi “Adaptive window selection for 3d shape recovery from image focus”, Optics and Laser Technology, vol. 45, pp. 21–31, 2013.
35. S.A. Lee, H.S. Jang and B.G. Lee “Jitter elimination in shape recovery by using adaptive neural network filter”, Sensors, vol. 19, no. 11, pp. 2566, 2019.
36. S. Pertuz, D. Puig and M.A. Garcia “Reliability measure for shape-from-focus”, Image and Vision Computing, vol. 31, no. 10, pp. 725–734, 2013.
37. M. Muhammad and T.S. Choi “Sampling for shape from focus in optical microscopy”, IEEE transactions on pattern analysis and machine intelligence, vol. 34, no. 3, pp. 564–573, 2012.
38. G. Easley, D. Labate, and W.Q. Lim “Sparse directional image representations using the discrete shearlet transform”, Applied and Computational Harmonic Analysis, vol. 25, no. 1, pp. 25– 46, 2008.