Estrategia evolutiva basada en gpu para la detección del disco óptico en imágenes de retina
DOI:
https://doi.org/10.22395/rium.v15n29a11Palabras clave:
gpu, disco óptico, estrategias evolutivas, imágenes de retinaResumen
La ejecución paralela de aplicaciones usando unidades de procesamiento gráfico (gpu) ha ganado gran interés en la comunidad académica en los años recientes. La computación paralela puede ser aplicada a las estrategias evolutivas para procesar individuos dentro de una población, sin embargo, las estrategias evolutivas se caracterizan por un significativo consumo de recursos computacionales al resolver problemas de gran tamaño o aquellos que se modelan mediante funciones de aptitud complejas. Este artÃculo describe la implementación de una estrategia evolutiva para la detección del disco óptico en imágenes de retina usando Compute Unified Device Architecture (cuda). Los resultados experimentales muestran que el tiempo de ejecución para la detección del disco óptico logra una aceleración de 5 a 7 veces, comparado con la ejecución secuencial en una cpu convencional.
Descargas
Los datos de descargas todavía no están disponibles.
Citas
[1] O. Kramer, “Evolution Strategies,†in A Brief Introduction to Continuous Evolutionary Optimization, Springer International Publishing, 2014, pp. 15–26.
[2] N. Hansen, D. V. Arnold, and A. Auger, “Evolution Strategies,†in Springer Handbook of Computational Intelligence, J. Kacprzyk and W. Pedrycz, Eds. Springer Berlin Heidelberg, 2015, pp. 871–898.
[3] G. Zeng and C. Ding, “An Analysis on Parallel Genetic Algorithm,†Computer Engineering, vol. 27, no. 9, pp. 53–55, 2001.
[4] Y. Ke, Y. Li, and D. Li, “Image Matching Using Genetic Algorithm on GPU,†in 2011 International Conference on Control, Automation and Systems Engineering (CASE), 2011, pp. 1–4.
[5] NVIDIA CUDA Compute Unified Device Architecture - Programming Guide. 2007.
[6] J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming, 1st ed. Addison-Wesley Professional, 2010.
[7] David Kirk and Wen-mei Hwu, Programming Massively Parallel Processors, 2nd ed. 2012.
[8] D. Robilliard, V. Marion-Poty, and C. Fonlupt, “Population Parallel GP on the G80 GPU,†in Genetic Programming, M. O’Neill, L. Vanneschi, S. Gustafson, A. I. E. Alcázar, I. D. Falco, A. D. Cioppa, and E. Tarantino, Eds. Springer Berlin Heidelberg, 2008, pp. 98–109.
[9] G. Chen, D. Xu, H. Hu, Y. Liu, and R. Chen, “The Application of CUDA Technology in Biomedical Image Processing,†in Emerging Research in Artificial Intelligence and Computational Intelligence, J. Lei, F. L. Wang, H. Deng, and D. Miao, Eds. Springer Berlin Heidelberg, 2012, pp. 378–385.
[10] M. A. Khan and A. Juhn, “Diabetic Retinopathy,†in Optical Coherence Tomography, A. Girach and R. C. Sergott, Eds. Springer International Publishing, 2016, pp. 29–42.
[11] L. Giancardo, F. Meriaudeau, T. P. Karnowski, Y. Li, S. Garg, K. W. Tobin Jr., and E. Chaum, “Exudate-based diabetic macular edema detection in fundus images using publicly available datasets,†Medical Image Analysis, vol. 16, no. 1, pp. 216–226, Jan. 2012.
[12] M. Krause, R. M. Alles, B. Burgeth, and J. Weickert, “Fast retinal vessel analysis,†J Real-Time Image Proc, vol. 11, no. 2, pp. 413–422, Apr. 2016.
[13] O. S. Soliman, J. Platoš, A. E. Hassanien, and V. Snášel, “Automatic Localization and Boundary Detection of Retina in Images Using Basic Image Processing Filters,†in Proceedings of the Third International Conference on Intelligent Human Computer Interaction (IHCI 2011), Prague, Czech Republic, August, 2011, M. Kudělka, J. Pokorný, V. Snášel, and A. Abraham, Eds. Springer Berlin Heidelberg, 2013, pp. 169–182.
[14] G. Sánchez Torres, A. Espinosa Bedoya, and Y. Fernando Ceballos, “DETECCIÓN DEL DISCO ÓPTICO EN RETINOGRAFÃAS MEDIANTE UNA ESTRATEGIA EVOLUTIVA (µ+λ),†Revista EIA, no. 21, pp. 55–66, Jun. 2014.
[15] M. D. Abramoff and M. Niemeijer, “The automatic detection of the optic disc location in retinal images using optic disc location regression,†in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2006. EMBS ’06, 2006, pp. 4432–4435.
[16] S. Sb and V. Singh, “Automatic Detection of Diabetic Retinopathy in Non-dilated RGB Retinal Fundus Images,†International Journal of Computer Applications, vol. 47, no. 19, pp. 26–32, Jun. 2012.
[17] C. Sinthanayothin, J. Boyce, H. Cook, and T. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,†Br J Ophthalmol, vol. 83, no. 8, pp. 902–910, Aug. 1999.
[18] A. Hoover and M. Goldbaum, “Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels,†IEEE Transactions on Medical Imaging, vol. 22, no. 8, pp. 951–958, Aug. 2003.
[19] C. Trujillo and J. Garcia-Sucerquia, “Graphics Processing Units: More Than the Pathway to Realistic Video-Games,†Dyna, vol. 78, no. 168, pp. 164–172, 2011.
[20] L. Zheng, Y. Lu, M. Ding, Y. Shen, M. Guoz, and S. Guo, “Architecture-based Performance Evaluation of Genetic Algorithms on Multi/Many-core Systems,†in 2011 IEEE 14th International Conference on Computational Science and Engineering (CSE), 2011, pp. 321–334.
[21] V. Kalesnykiene, J. –. Kamarainen, R. Voutilainen, J. Pietilä, H. Kälviäinen, and H. Uusitalo, DIARETDB1 diabetic retinopathy database and evaluation protocol. 2012.
[22] Narendra V G and Hareesh K S, “Study and comparison of various image edge detection techniques used in quality inspection and evaluation of agricultural and food products by computer vision,†Int J Agric & Biol Eng, vol. 4, pp. 83–90.
[23] W. B. Langdon, “A Fast High Quality Pseudo Random Number Generator for nVidia CUDA,†in Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers, New York, NY, USA, 2009, pp. 2511–2514.
[2] N. Hansen, D. V. Arnold, and A. Auger, “Evolution Strategies,†in Springer Handbook of Computational Intelligence, J. Kacprzyk and W. Pedrycz, Eds. Springer Berlin Heidelberg, 2015, pp. 871–898.
[3] G. Zeng and C. Ding, “An Analysis on Parallel Genetic Algorithm,†Computer Engineering, vol. 27, no. 9, pp. 53–55, 2001.
[4] Y. Ke, Y. Li, and D. Li, “Image Matching Using Genetic Algorithm on GPU,†in 2011 International Conference on Control, Automation and Systems Engineering (CASE), 2011, pp. 1–4.
[5] NVIDIA CUDA Compute Unified Device Architecture - Programming Guide. 2007.
[6] J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming, 1st ed. Addison-Wesley Professional, 2010.
[7] David Kirk and Wen-mei Hwu, Programming Massively Parallel Processors, 2nd ed. 2012.
[8] D. Robilliard, V. Marion-Poty, and C. Fonlupt, “Population Parallel GP on the G80 GPU,†in Genetic Programming, M. O’Neill, L. Vanneschi, S. Gustafson, A. I. E. Alcázar, I. D. Falco, A. D. Cioppa, and E. Tarantino, Eds. Springer Berlin Heidelberg, 2008, pp. 98–109.
[9] G. Chen, D. Xu, H. Hu, Y. Liu, and R. Chen, “The Application of CUDA Technology in Biomedical Image Processing,†in Emerging Research in Artificial Intelligence and Computational Intelligence, J. Lei, F. L. Wang, H. Deng, and D. Miao, Eds. Springer Berlin Heidelberg, 2012, pp. 378–385.
[10] M. A. Khan and A. Juhn, “Diabetic Retinopathy,†in Optical Coherence Tomography, A. Girach and R. C. Sergott, Eds. Springer International Publishing, 2016, pp. 29–42.
[11] L. Giancardo, F. Meriaudeau, T. P. Karnowski, Y. Li, S. Garg, K. W. Tobin Jr., and E. Chaum, “Exudate-based diabetic macular edema detection in fundus images using publicly available datasets,†Medical Image Analysis, vol. 16, no. 1, pp. 216–226, Jan. 2012.
[12] M. Krause, R. M. Alles, B. Burgeth, and J. Weickert, “Fast retinal vessel analysis,†J Real-Time Image Proc, vol. 11, no. 2, pp. 413–422, Apr. 2016.
[13] O. S. Soliman, J. Platoš, A. E. Hassanien, and V. Snášel, “Automatic Localization and Boundary Detection of Retina in Images Using Basic Image Processing Filters,†in Proceedings of the Third International Conference on Intelligent Human Computer Interaction (IHCI 2011), Prague, Czech Republic, August, 2011, M. Kudělka, J. Pokorný, V. Snášel, and A. Abraham, Eds. Springer Berlin Heidelberg, 2013, pp. 169–182.
[14] G. Sánchez Torres, A. Espinosa Bedoya, and Y. Fernando Ceballos, “DETECCIÓN DEL DISCO ÓPTICO EN RETINOGRAFÃAS MEDIANTE UNA ESTRATEGIA EVOLUTIVA (µ+λ),†Revista EIA, no. 21, pp. 55–66, Jun. 2014.
[15] M. D. Abramoff and M. Niemeijer, “The automatic detection of the optic disc location in retinal images using optic disc location regression,†in 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2006. EMBS ’06, 2006, pp. 4432–4435.
[16] S. Sb and V. Singh, “Automatic Detection of Diabetic Retinopathy in Non-dilated RGB Retinal Fundus Images,†International Journal of Computer Applications, vol. 47, no. 19, pp. 26–32, Jun. 2012.
[17] C. Sinthanayothin, J. Boyce, H. Cook, and T. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,†Br J Ophthalmol, vol. 83, no. 8, pp. 902–910, Aug. 1999.
[18] A. Hoover and M. Goldbaum, “Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels,†IEEE Transactions on Medical Imaging, vol. 22, no. 8, pp. 951–958, Aug. 2003.
[19] C. Trujillo and J. Garcia-Sucerquia, “Graphics Processing Units: More Than the Pathway to Realistic Video-Games,†Dyna, vol. 78, no. 168, pp. 164–172, 2011.
[20] L. Zheng, Y. Lu, M. Ding, Y. Shen, M. Guoz, and S. Guo, “Architecture-based Performance Evaluation of Genetic Algorithms on Multi/Many-core Systems,†in 2011 IEEE 14th International Conference on Computational Science and Engineering (CSE), 2011, pp. 321–334.
[21] V. Kalesnykiene, J. –. Kamarainen, R. Voutilainen, J. Pietilä, H. Kälviäinen, and H. Uusitalo, DIARETDB1 diabetic retinopathy database and evaluation protocol. 2012.
[22] Narendra V G and Hareesh K S, “Study and comparison of various image edge detection techniques used in quality inspection and evaluation of agricultural and food products by computer vision,†Int J Agric & Biol Eng, vol. 4, pp. 83–90.
[23] W. B. Langdon, “A Fast High Quality Pseudo Random Number Generator for nVidia CUDA,†in Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers, New York, NY, USA, 2009, pp. 2511–2514.
Descargas
Archivos adicionales
Publicado
2016-07-14
Cómo citar
Sánchez-Torres, G., & González-Calederón, G. (2016). Estrategia evolutiva basada en gpu para la detección del disco óptico en imágenes de retina. Revista IngenierÃas Universidad De MedellÃn, 15(29), 173–190. https://doi.org/10.22395/rium.v15n29a11
Número
Sección
ArtÃculos
Licencia
Queda autorizada la reproducción total o parcial de los contenidos de la revista con finalidades educativas, investigativas o académicas siempre y cuando sea citada la fuente. Para poder efectuar reproducciones con otros propósitos, es necesario contar con la autorización expresa del Sello Editorial Universidad de MedellÃn.
