CUDA Based Computation of Quadratic Image Filters

Abstract

Image processing applications usually requires nonlinear methods due to the nonlinear characteristics of images. Quadratic image filter which is a class of nonlinear image filters are widely used in practice such as noise elimination edge detection and image enhancement. On the other hand, second order products of the pixels make quadratic image filters computationally expensive to implement when compared to linear convolution. In the last decade, CUDA accelerated computing has been widely used in image processing applications to reduce computation times. In this study, an efficient method for the CUDA acceleration of the quadratic image filter has been implemented. For this purpose, alternative algorithms were examined comparatively since the performance of the GPU is sensitive to memory utilization. Because quadratic filter has a large number of coefficients and quadratic terms, the algorithm which utilizes the shared memory for storing image blocks provided the best throughput among the examined methods. Comparative results that were obtained using various images in different sizes show significant accelerations over sequential implementation.

Keywords

• Quadratic Image Filter, CUDA,GPU computing,Volterra filter

References

1. J. C. Russ, The image processing handbook. CRC press, 2016.
2. I. Pitas and A. N. Venetsanopoulos, Nonlinear digital filters: principles and applications, vol. 84. Springer Science & Business Media, 2013.
3. G. F. Ramponi, G. L. Sicuranza, and W. Ukovich, “A computational method for the design of 2-D nonlinear Volterra filters,” Circuits Syst. IEEE Trans., vol. 35, no. 9, pp. 1095–1102, 1988.
4. L. Thomas, G. Krishnan, R. A. Mol, and A. Roy, “Removal of Impulsive Noise from MRI Images using Quadratic Filter,” Int. J. Eng. Res. Technol., vol. 3, no. 4, pp. 2220–2223, 2014.
5. M. Meenavathi and K. Rajesh, “Volterra Filtering techniques for removal of Gaussian and mixed Gaussian-Impulse noise,” Int. J. Electr. Comput. Eng., vol. 1, no. 2, pp. 184–190, 2007.
6. J. Zhang and Y. Pang, “Pipelined robust M-estimate adaptive second-order Volterra filter against impulsive noise,” Digit. Signal Process., vol. 26, pp. 71–80, Mar. 2014.
7. V. S. Hari, V. P. Jagathy Raj, and R. Gopikakumari, “Quadratic filter for the enhancement of edges in retinal images for the efficient detection and localization of diabetic retinopathy,” Pattern Anal. Appl., vol. 20, no. 1, pp. 145–165, Feb. 2017.
8. V. S. Hari, V. P. Jagathy Raj, and R. Gopikakumari, “Unsharp masking using quadratic filter for the enhancement of fingerprints in noisy background,” Pattern Recognit., vol. 46, no. 12, pp. 3198–3207, Dec. 2013.

9. Y. Zhou, K. Panetta, and S. Agaian, “Mammogram enhancement using alpha weighted quadratic filter,” in Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009, 2009, pp. 3681–3684.
10. A. Pandey, A. Yadav, and V. Bhateja, “Design of new volterra filter for mammogram enhancement,” in Advances in Intelligent Systems and Computing, 2013, vol. 199 AISC, pp. 143–151.
11. M. Kanamadi, V. Waghamode, and S. Bandekar, “Alpha Weighted Quadratic Filter Based Enhancement for Mammogram,” in Proceedings of International conference on “Emerging Research in Computing, Information, Communication and Applications” (ERCICA), 2013, pp. 68–74.
12. V. Bhateja, M. Misra, S. U.-C. methods and programs in, and undefined 2016, “Non-linear polynomial filters for edge enhancement of mammogram lesions,” Comput. Methods Programs Biomed., no. 129, pp. 125-134., 2016.
13. V. S. Hari, R. V. P. Jagathy, and R. Gopikakumari, “Enhancement of calcifications in mammograms using Volterra series based quadratic filter,” in Proceedings - 2012 International Conference on Data Science and Engineering, ICDSE 2012, 2012, pp. 85–89.
14. G. Jothilakshmi and E. Gopinathan, “Mammogram Enhancement Using Quadratic Adaptive Volterra Filter A Comparative Analysis In Spatial And Frequency Domain,” ARPN J. Eng. Appl. Sci., vol. 10, no. 13, pp. 5512–5517, 2006.
15. V. Bhateja, M. Misra, S. Urooj, and A. Lay-Ekuakille, “A robust polynomial filtering framework for mammographic image enhancement from biomedical sensors,” IEEE Sens. J., vol. 13, no. 11, pp. 4147–4156, 2013.
16. A. Chakrabarty, H. Jain, and A. Chatterjee, “Volterra kernel based face recognition using artificial bee colonyoptimization,” Eng. Appl. Artif. Intell., vol. 26, no. 3, pp. 1107–1114, 2013.
17. G. Feng, H. Li, J. Dong, and J. Zhang, “Face recognition based on Volterra kernels direct discriminant analysis and effective feature classification,” Inf. Sci. (Ny)., vol. 441, pp. 187–197, 2018.
18. G. Feng, H. Li, J. Dong, and J. Zhang, “Direct discriminant analysis using volterra kernels for face recognition,” in Communications in Computer and Information Science, 2016, vol. 662, pp. 404–412.
19. G. Sicuranza and G. Ramponi, “Adaptive nonlinear digital filters using distributed arithmetic,” IEEE Trans. Acoust., 1986.
20. G. Ramponi, “Edge extraction by a class of second-order nonlinear filters,” Electron. Lett., vol. 9, no. 22, pp. 482–484, 1986.
21. S. Mitra, “Image processing using quadratic volterra filters,” in Computers and Devices for Communication (CODEC), 2012 5th International Conference on, 2012, pp. 1–2.
22. T. Kalaiselvi, P. Sriramakrishnan, and K. Somasundaram, “Survey of using GPU CUDA programming model in medical image analysis,” Informatics Med. Unlocked, vol. 9, pp. 133–144, Jan. 2017.
23. M. Soua, R. Kachouri, and M. Akil, “GPU parallel implementation of the new hybrid binarization based on Kmeans method (HBK),” J. Real-Time Image Process., vol. 14, no. 2, pp. 363–377, Feb. 2018.
24. A. HajiRassouliha, A. J. Taberner, M. P. Nash, and P. M. F. Nielsen, “Suitability of recent hardware accelerators (DSPs, FPGAs, and GPUs) for computer vision and image processing algorithms,” Signal Process. Image Commun., vol. 68, pp. 101–119, Oct. 2018.
25. Y. Zhou, F. He, and Y. Qiu, “Accelerating image convolution filtering algorithms on integrated CPU–GPU architectures,” J. Electron. Imaging, vol. 27, no. 03, p. 1, May 2018.
26. O. Green, “Efficient scalable median filtering using histogram-based operations,” IEEE Trans. Image Process., vol. 27, no. 5, pp. 2217–2228, 2017.
27. F. Bozkurt, M. Yaganoglu, and F. B. Günay, “Effective Gaussian Blurring Process on Graphics Processing Unit with CUDA,” Int. J. Mach. Learn. Comput., vol. 5, no. 1, p. 57, 2015.
28. P. S. Battiato, “High Performance Median Filtering Algorithm Based on NVIDIA GPU Computing,” in International Symposium for Young Scientists in Technology, Engineering and Mathematics, 2016, pp. 1–10.
29. W. Ling, Nonlinear digital filters: analysis and applications. Academic Press, 2010.
30. G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library. “ O’Reilly Media, Inc.,” 2008.
31. S. Uzun and D. Akgün, “An Accelerated Method for Determining the Weights of Quadratic Image Filters,” IEEE Access, vol. 6, pp. 33718–33726, 2018.
32. J. Cheng, M. Grossman, and T. KcKercher, Professional CUDA C programming. Wrox, 2014.