Parallelization of retina fundus image skeletonization in CUDA architecture

Authors

  • Karin Satie Komati Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil. https://orcid.org/0000-0001-5677-4724
  • Flavio Severiano Lamas de Souza Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.
  • Juliana Amorim Guimarães Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.
  • Jefferson Oliveira Andrade Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil. https://orcid.org/0000-0002-5321-9239

DOI:

https://doi.org/10.5965/2764747102032013075

Keywords:

skeletonization algorithm, Zhang-Suen, digital retinal images, CUDA, DRIVE

Abstract

This work presents a comparative analysis of the response time for the skeletonization of images, using two versions of the Zhang-Suen algorithm: a sequential mono-processed version and an parallel multi-processed version using the graphics processing unit. The parallel computing platform chosen was CUDA. The skeletonization applications developed is aimed towards processing retinal images, whose characteristics are extracted of blood vessels to assist medical diagnosis, and thus the response time of the system is paramount. Tests were performed on the DRIVE public retinal images database, and showed that the parallel version of the algorithm was, on average, more than 31 times faster than the sequential version.

Downloads

Download data is not yet available.

Author Biographies

Karin Satie Komati, Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.

Graduated in Electrical Engineering at the Espírito Santo Federal University, UFES, Brazil.

Has a Master’s degree in Informatics from the Espírito Santo Federal University, UFES, Brazil.

Graduated in Electrical Engineering at the Espírito Santo Federal University, UFES, Brazil.

Graduated in Computing Sciences at the Espírito Santo Federal University, UFES, Brazil.

Professor at the Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.

Flavio Severiano Lamas de Souza, Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.

PhD in Education from Universidad del Norte - UniNorte, UniNorte, Paraguay.

Has a Master’s degree in Informatics from the Espírito Santo Federal University, UFES, Brazil.

Graduated in Computing Sciences at the Espírito Santo Federal University, UFES, Brazil.

Professor at the Federal Institute of Education, Science, and Technology of Espírito Santo, IFES, Brazil.

Juliana Amorim Guimarães, Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.

Has a Master’s degree in Informatics from the Espírito Santo Federal University, UFES, Brazil.

Graduated in Information Systems at the Federal Institute of Education, Science, and Technology of Espírito Santo, IFES, Brazil.

Jefferson Oliveira Andrade, Federal Institute of Education, Science and Technology of Espírito Santo, IFES, Brazil.

PhD in Education from Universidad del Norte - UniNorte, UniNorte, Paraguay.

Has a Master’s degree in Informatics from the Espírito Santo Federal University, UFES, Brazil.

Graduated in Computing Sciences at the Espírito Santo Federal University, UFES, Brazil.

Professor at the Espírito Santo Education, Science, and Technology Federal Institute, IFES, Brazil.

References

RF. Illustration of the human eye anatomy. Disponível em: http://www.123rf.com/photo_20185366_illustration-of-the-human-eye-anatomy.html. Acesso em: junho 2013.

CORRÊA, F. P.; FESTA, L. M. Avaliação de Técnicas para Afinamento de Imagens Digitais. Trabalho de Conclusão de Curso de Bacharelado em Ciência da Computação da Universidade Federal do Paraná, 2005.

DUTRA, E. R. F., VARINI, A. L., CANAL, A. P. Paralelização de aplicações na arquitetura cuda: um estudo sobre vetores. In: XVI SIMPÓSIO DE ENSINO, PESQUISA E EXTENSÃO (SEPE 2012), 2012. Santa Maria/RS.

ITSEEZ. OpenCV. Disponível em: http://opencv.org/. Acesso em: out. 2012.

GONZALEZ, R. C., WOODS, R. E. Digital image processing. 3ª ed. Prentice Hall, Upper Saddle River, NJ, 2008. 716p.

GUIMARÃES, J. A.; SOUZA, F. S. L.; KOMATI, K. S. Identificação de Pontos de Bifurcação em Vasos Sanguíneos de Imagens de Retina Usando Algoritmo de Esqueletização. In: III ERI-MT 2012 Escola Regional de Informática do SBC (Regional Mato Grosso), 2012, Rondonópolis. Anais do III ERI-MT 2012 Escola Regional de Informática do SBC (Regional Mato Grosso), 2012.

GULO, C. A. S. J., ARRUDA, H. F. de A., SEMENTILLE, A. C. , ARAUJO, A. F., TAVARES, J. M. R. S. Método de Suavização de Imagem baseado num Modelo Variacional Paralelizado em Arquitetura CUDA. In: XXXII Congresso da Sociedade Brasileira de Computação, GPU Computing Developer Forum (CSBC 2012), 2012. Curitiba/PR.

NUGTEREN, C., CORPORAAL, H., MESMAN, B., Skeleton-based automatic parallelization of image processing algorithms for GPUs. In: XI International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, (ICSAMOS 2011), 2011, Samos, Greece. p. 25-32.

NVIDIA. GeForce GTS 450. Disponível em: http://www.nvidia.com.br/object/product-geforce-gts-450-br.html. Acesso em: out. 2012.

NVIDIA. Cuda. Disponível em: http://www.nvidia.com.br/object/cuda_home_new_br.html. Acesso em: out. 2012.

PALOMERA-PEREZ, M. A., MARTINEZ-PEREZ, M. E., BENITEZ-PEREZ, H., ORTEGA-ARJONA, J. L.. Parallel multiscale feature extraction and region growing: application in retinal blood vessel detection. IEEE Transactions on Information Technology in Biomedicine. 14(2):500-506, 2010.

PILLA, L. L. Análise de Desempenho da Arquitetura CUDA Utilizando os NAS Parallel. Trabalho de Conclusão (Graduação em Ciência da Computação). Instituto de Informática, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre. 2009.

STAAL, J. J.; ABRAMOFF, M. D.; NIEMEIJER, M.; VIERGEVER, M. A.; VAN GINNEKEN, B. Ridge based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging, vol. 23, pp. 501-509. 2004.

THYPARAMPIL, P. J., PARK, Y., MARTINEZ-PEREZ, M. E., LEE, T. C., WEISSGOLD, D. J., BERROCAL, A. M., CHAN, R. V. P., FLYNN, J. T., CHIANG, M. F. Plus Disease in Retinopathy of Prematurity: Quantitative Analysis of Vascular Change. American Journal of Ophthalmology. 150(4):468-475.e2, 2010.

WIKIMEDIA COMMONS. File:CUDA processing flow (En).PNG. Disponível em: http://en.wikipedia.org/wiki/File:CUDA_processing_flow_(En).PNG. Acesso em: junho 2013.

ZEPEDA-ROMERO, L. C., MARTINEZ-PEREZ, M. E., RUIZ-VELASCO, S., RAMIREZ-ORTIZ, M. A.; GUTIERREZ-PADILLA, J. A. Temporary morphological changes in plus disease induced during contact digital imaging. Eye. 25(10):1337-1340, 2011.

ZHANG T.Y; SUEN C.Y. A Fast Parallel Algorithm for Thinning Digital Patterns, Communications of ACM, vol 27, nº 3, pp 236-239, 1984.

Published

2013-08-06

How to Cite

Komati, K. S., Souza, F. S. L. de, Guimarães, J. A., & Andrade, J. O. (2013). Parallelization of retina fundus image skeletonization in CUDA architecture. Revista Brasileira De Contabilidade E Gestão, 2(3), 75–85. https://doi.org/10.5965/2764747102032013075

Issue

Section

Articles