access icon free Image feature extraction algorithm based on CUDA architecture: case study GFD and GCFD

Optimising computing times of applications is an increasingly important task in many different areas such as scientific and industrial applications. Graphics processing unit (GPU) is considered as one of the powerful engines for computationally demanding applications since it proposes a highly parallel architecture. In this context, the authors introduce an algorithm to optimise the computing time of feature extraction methods for the colour image. They choose generalised Fourier descriptor (GFD) and generalised colour Fourier descriptor (GCFD) models, as a method to extract the image feature for various applications such as colour object recognition in real-time or image retrieval. They compare the computing time experimental results on central processing unit and GPU. They also present a case study of these experimental results descriptors using two platforms: a NVIDIA GeForce GT525M and a NVIDIA GeForce GTX480. Their experimental results demonstrate that the execution time can considerably be reduced until 34× for GFD and 56× for GCFD.

Inspec keywords: parallel architectures; feature extraction; Fourier transforms; image colour analysis

Other keywords: GPU; image retrieval; NVIDIA GeForce GTX480; parallel architecture; colour object recognition; GCFD; colour image; generalised colour Fourier descriptor models; Clifford–Fourier transform; GFD; graphics processing unit; image feature extraction algorithm; NVIDIA GeForce GT525M; generalised Fourier descriptor; central processing unit; CUDA architecture

Subjects: Integral transforms; Parallel architecture; Image recognition; Integral transforms; Computer vision and image processing techniques

References

    1. 1)
      • 8. NVIDIA Corporation: ‘CUFFT LIBRARY USER'S GUIDE version 6.5’ (NVIDIA, 2014), pp. 176.
    2. 2)
      • 12. NVIDIA Corporation: ‘CUDA C PROGRAMMING GUIDE version 6.5’ (NVIDIA, 2014), pp. 1241.
    3. 3)
      • 4. Batard, T., Berthier, M., Saint-Jean, C.: ‘Clifford–Fourier transform for color image processing’, in (EDs.): ‘Geometric algebra computing’ (Springer-Verlag London Press, 2010, 1st edn.), pp. 135162.
    4. 4)
      • 9. Haythem, B., Fatma, S., Marwa, C., et al: ‘Accelerating Fourier descriptor for image recognition using GPU’, Appl. Math. Inf. Sci., 2016, 10, (1), pp. 297306.
    5. 5)
      • 14. NVIDIA Corporation: ‘Profiler user's guide’ (NVIDIA, 2014), pp. 187.
    6. 6)
      • 2. NVIDIA Corporation: ‘NVIDIA CUDA_6.5_Performance_Report Version 6.5’ (NVIDIA, 2014), pp. 130.
    7. 7)
      • 1. Pereira, A.D., Ramos, L., GÓES, L.: ‘PSkel: a stencil programming framework for CPU-GPU systems’, Concurrency Comput. Pract. Exp., 2015, 27, (17), pp. 49384953.
    8. 8)
      • 15. Smach, F.: ‘Etude et implantation FPGA des descripteurs de Fourier généralisés combinés aux SVM’. PhD thesis, Burgundy University, 2007.
    9. 9)
      • 7. Haythem, B., Mohamed, H., Marwa, C., et al: ‘Fast generalized Fourier descriptor for object recognition of image using CUDA’. 2014 World Symp. Computer Applications and Research, January 2014, pp. 15.
    10. 10)
      • 10. Chouchene, M., Sayadi, F.E., Bahri, H., et al: ‘Optimized parallel implementation of face detection based on GPU component’, Microprocess. Microsyst.., 2015, 39, (6), pp. 393404.
    11. 11)
      • 5. Mennesson, J., Saint-Jean, C., Mascarilla, L.: ‘Color object recognition based on a Clifford–Fourier transform’, in (EDs.): ‘Guide to geometric algebra in practice’ (Springer-Verlag London Press, 2011, 1st edn.), pp. 175191.
    12. 12)
      • 13. CUDA Occupancy Calculator. Available at http://www.developer.download.nvidia.com/compute/cuda/CUDA_Occupancy_calculator.xls, accessed 14 November 2016.
    13. 13)
      • 11. Zhang, D., Lul, G.: ‘Shape based image retrieval using generic Fourier descriptor’, Signal Process., Image Commun., 2002, 17, (10), pp. 825848.
    14. 14)
      • 3. Smach, F., Miteran, J., Atri, M., et al: ‘An FPGA-based accelerator for Fourier descriptors computing for color object recognition using SVM’, J. Real-Time Image Process., 2007, 2, (4), pp. 249258.
    15. 15)
      • 6. Mohamed, H., Mohamed, A., Smach, F.: ‘Hardware implementation of GCFD for color images recognition’. 2014 World Congress Computer Applications and Information Systems, January 2014, pp. 15.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cdt.2016.0135
Loading

Related content

content/journals/10.1049/iet-cdt.2016.0135
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading