Fast computation of 2D and 3D Legendre moments using multi-core CPUs and GPU parallel architectures
Tóm tắt
Legendre moments and their invariants for 2D and 3D image/objects are widely used in image processing, computer vision, and pattern recognition applications. Reconstruction of digital images by nature required higher-order moments to get high-quality reconstructed images. Different applications such as classification of bacterial contamination images utilize high-order moments for feature extraction phase. For big size images and 3D objects, Legendre moments computation is very time-consuming and compute-intensive. This problem limits the use of Legendre moments and makes them impractical for real-time applications. Multi-core CPUs and GPUs are powerful processing parallel architectures. In this paper, new parallel algorithms are proposed to speed up the process of exact Legendre moments computation for 2D and 3D image/objects. These algorithms utilize multi-core CPUs and GPUs parallel architectures where each pixel/voxel of the input digital image/object can be handled independently. A detailed profile analysis is presented where the weight of each part of the entire computational process is evaluated. In addition, we contributed to the parallel 2D/3D Legendre moments by: (1) a modification of the traditional exact Legendre moment algorithm to better fit the parallel architectures, (2) we present the first parallel CPU implementation of Legendre moment, and (3) we present the first parallel CPU and GPU acceleration of the reconstruction phase of the Legendre moments. A set of numerical experiments with different gray-level images are performed. The obtained results clearly show a very close to optimal parallel gain. The extreme reduction in execution times, especially for 8-core CPUs and GPUs, makes the parallel exact 2D/3D Legendre moments suitable for real-time applications.
Tài liệu tham khảo
Flusser, J., Suk, T., Zitov, B.: Moments and Moment Invariants in Pattern Recognition. Wiley, Chichester (2009)
Talenti, G.: Recovering a function from a finite number of moments. Inverse Probl. 3, 501–517 (1987)
Pawlak M.: Image analysis by moments: reconstruction and computational aspects. Oficyna Wydawnicza Politechniki Wroclawskiej. 38–42 (2006)
Shin, HC., et al.: Interleaved text/image deep mining on a very large-scale radiology database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1090–1099 (2015)
Toharia, P., et al.: Shot boundary detection using Zernike moments in multi-GPU multi-CPU architectures. J. Parallel Distrib. Comput. 72(9), 1127–1133 (2012)
Dongfeng, X., et al.: Parallel computation for discrete orthogonal moments of images using graphic processing unit. J. Inf. Comput. Sci. 9(3), 611–618 (2012)
Heidari, H., Chalechale, A., Mohammad abadi, A.A.: Parallel implementation of color based image retrieval using CUDA on the GPU. Int. J. Inf. Technol. Comput. Sci. 6(1), 33 (2013)
Teodoro, G., et al. High-throughput analysis of large microscopy image datasets on CPU–GPU cluster platforms. In: 2013 IEEE 27th International Symposium on Parallel Distributed Processing (IPDPS). IEEE (2013)
Martin-Requena, M.J., Ujaldon, M.: High performance computation of moments for an accurate classification of bone tissue images. In: 2011 IEEE 13th International Conference on High Performance Computing and Communications (HPCC). IEEE (2011)
Mustapha, H., Dimitrakopoulos, R.: HOSIM: a high-order stochastic simulation algorithm for generating three-dimensional complex geological patterns. Comput. Geosci. 37(9), 1242–1253 (2011)
Srinivasa Rao, C.H.S., Kumar, S.S., Mohan, B.C.: Content based image retrieval using exact legendre moments and support vector machine. Int. J. Multimed. Appl. 2(2), 69–79 (2010)
Hosny, K.M.: Robust template matching using orthogonal Legendre moment invariants. J. Comput. Sci. 6(10), 1080–1084 (2010)
Wojak, J., Angelini, E.D., Bloch, I.: Introducing Shape Constraint via Legendre Moments in a Variational Framework for Cardiac Segmentation on Non-contrast CT Images, pp. 209–214. VISAPP, Angers (2010)
Nakib, A., Schulze, Y., Petit, E.: Image thresholding framework based on two-dimensional digital fractional integration and Legendre moments. IET Image Process. 6(8), 717–727 (2012)
Dahdouha, S., Angelinia, E.D., Grangéb, G., Blocha, I.: Segmentation of embryonic and fetal 3D ultrasound images based on pixel intensity distributions and shape priors. Med. Image Anal. 24(1), 255–268 (2015)
Vijayalakshmi, B., Bharathi, V.S.: Classification of CT liver images using local binary pattern with Legendre moments. Curr. Sci. 110(4), 687–691 (2016)
Hosny, K. M., Papakostas, G. A., Koulouriotis, D. E.: Accurate reconstruction of noisy medical images using orthogonal moments. In: 18th International Conference on Digital Signal Processing (DSP), (2013)
Sastry, S.S., Mallika, K., Rao, B.G.S., Ha, S.T., Lakshminarayana, S.: Novel approach to study liquid crystal phase transitions using Legendre moments. Phase Transit. 85(8), 735–749 (2012)
Hosny, K.M.: Exact Legendre moment computation for gray level images. Pattern Recognit. 40(12), 3597–3605 (2007)
Papakostas, G.A., Karakasis, E.G., Koulouriotis, D.E.: Accurate and speedy computation of image Legendre moments for computer vision applications. Image Vis. Comput. 29(3), 414–423 (2010)
Hosny, K.M.: Fast and low-complexity method for exact computation of 3D Legendre moments. Pattern Recognit. Lett. 32(9), 1305–1314 (2011)
Bahaoui, Z., Zenkouar, K., Fadili, H., Qjidaa, H., Zarghili A.: Blocking artifact removal using partial overlapping based on exact Legendre moments computation. J. Real Time Image Process. 1–19 (2014). doi:10.1007/s11554-014-0465-3
Lachiondo, J.A., Ujaldóna, M., Berrettab, R., Moscatob, P.: Legendre moments as high performance bone biomarkers: computational methods and GPU acceleration. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 4(3-4), 146–163 (2016)
Hosny, K.M.: New set of rotationally Legendre moment invariants. Int. J. Electr. Electron. Eng. 4, 176–180 (2010)
Hosny, K.M.: Refined translation and scale Legendre moment invariants. Pattern Recognit. Lett. 31(7), 533–538 (2010)
Zhang, H., Shu, H., Coatrieux, G., Zhu, J., Wu, Q.M.J., Zhang, Y., Zhu, H., Luo, L.: Affine Legendre moment invariants for image watermarking robust to geometric distortions. IEEE Trans. Image Process. 20(8), 2189–2199 (2011)
Spiegel, M.R.: Schaum’s Handbook of Formulas and Tables. MacGraw Hill, New York (1968)
Bossen, D.C., Kitamorn, A., Reick, K.F., et al.: Fault-tolerant design of the IBM Series 690 system using POWER4 processor technology. IBM J. Res. Dev. 46(1), 77–86 (2002)
Vajda, A.: Multi-core and Many-core Processor Architectures, pp. 9–43. Springer, Berlin (2011)
Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46–55 (1998)
Wen-Mei, W.H.: GPU Computing Gems, Emerald edn, pp. 5–10. Elsevier, Amsterdam (2011)
Zhu, X., et al.: Parallel implementation of MAFFT on CUDA-enabled graphics hardware. IEEE/ACM Trans. Comput. Biol. Bioinform. (TCBB) 12(1), 205–218 (2015)
Hosny, K.M.: Fast computation of accurate Zernike moments. J. Real Time Image Process. 3(1), 97–107 (2008)
Hosny, K.M.: New set of Gegenbauer moment invariants for pattern recognition applications. Arab. J. Sci. Eng. 39, 7097–7107 (2014)
http://wang.ist.psu.edu/docs/home.shtml (2016). Accessed 13 Dec 2016
Lazebnik, S., Schmid, C., Ponce, J.: Semi-local affine parts for object recognition. In: Proceedings of the British Machine Vision Conference, vol. 2, pp. 959–968, (2004)