Skip to main content
SpringerLink
Log in

Enhanced Configurable DCT Cordic Loeffler Architectures for Optimal Power-PSNR Trade-Off

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

The Discrete Cosine Transform (DCT) is one of the most widely used techniques of transforms in digital signal processing. It is the main algorithm in image and video coding systems. In this paper, we propose an algorithm which generates enhanced Cordic based Loeffler DCT architectures for angle’s precision degrees ranging from 10−1 to 10−7. High level PSNR, area and power estimators have been proposed to make a trade-off between consumption and image quality. An optimal architecture has been retained for its low complexity, low power and high PSNR. The complexity of this architecture is the lowest among the conventional DCT architectures even the BinDCT which is a reference in terms of reduced complexity. The selected architecture has also the closest PSNR to the reference Loeffler-DCT architecture without a substancial loss of power.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16

Similar content being viewed by others

References

  1. Loeffler, C., Lightenberg, A., & Moschytz, G.S. (1989). Practical fast 1-D DCT algorithms with 11-multiplications (Vol. 2, pp. 988–991). Glasgow UK: Proceedings ICASSP.

  2. Jeong, H., Kim, J., & Cho, W. K. (2004). Low-power multiplierless DCT architecture using image correlation. IEEE Transactions of Consumer Electronics, 50(1), 262–267.

    Article  Google Scholar 

  3. Arathanasis, H. C. (1993). On computing the 2-D Discrete Cosine Transform Using Rotations, Microprocessors and Microprogramming 38.

  4. Volder, J. E. (1959). The CORDIC trigonometric computing technique. IRE Electronics Packaging Computer, EC-8, 330–334.

    Article  Google Scholar 

  5. Walther, J. (1971). A unified algorithm for elementary functions. Proceedings Spring Joint Computer Conference, 38, 379–385.

    Google Scholar 

  6. Mariatos, E. P., Metafas, D. E., Hallas, J. A., & Goutis, C. E. (1994). A fast DCT processor, based on special purpose CORDIC rotators. Proceedings of IEEE International Symposium Circuits System, 4, 271–274.

    Article  Google Scholar 

  7. Sun, C.-C., Ruan, S.-J., Heyne, B., & Goetze, J. (2007). Low-power and high quality Cordic-based Loeffler DCT for signal processing. IET Circuits Devices System, 1(6), 453–461.

    Article  Google Scholar 

  8. Sun, C. -C., Donner, P., & Götze, J. (2012). VLSI implementation of a configurable IP Core for quantized discrete cosine and integer transforms. International Journal of Circuit Theory and Applications, 40(11), 1107–1126.

    Article  Google Scholar 

  9. Dang, P. P., Chau, P. M., Nguyen, T. Q., & Tran, T. D. (2005). BinDCT and its efficient VLSI architectures for real-time embedded applications. Journal Image Science and Technology, 49(2), 124–137.

    Google Scholar 

  10. Fritts, J. E., Steiling, F. W., Tucek, J. A., & Wolf, W (2009). MediaBench II video: Expediting the next generation of video systems research. Microprocessors and Microsystems, 33(4), 301–318.

    Article  Google Scholar 

  11. Deng, L., Sobti, K., Chakrabarti, C., & Zhang, Y. (2011). Accurate Area, Time and Power Models for FPGA-Based Implementations, Journal Sign Process System.

  12. Lee, M. -W., Yoon, J. -H., & Park, J. (2014). Reconfigurable CORDIC-Based Low-Power DCT Architecture Based on Data Priority. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 22(5), 1060–1068.

    Article  Google Scholar 

  13. Shafique, M., Bauer, L., & Henkel, J. (2008). Optimizing the H.264/AVC Video Encoder Application Structure for Reconfigurable and Application- Specific Platforms, Journal of Signal Processing Systems (JSPS).

  14. Shafique, M., Bauer, L., & Henkel, J. (2010). Optimizing the H.264/AVC Video Encoder Application Structure for Reconfigurable and Application-Specific Platforms, Journal Sign Process System.

  15. Fang, J. T., Tsai, Y. C., Lee, J. X., & Yu, P. S. (2016). Computation Reduction in Transform Unit of High Efficiency Video Coding based on Zero coefficients , International Symposium on Computer, Consumer and Control.

  16. Liu, Y. Y., Chen, H. X., Zhao, Y., & Sun, H. Y. (2015). Discrete cosine transform optimization in image compression based on genetic algorithm, 8th International Congress on Image and Signal Processing (CISP).

  17. Meeuws, R., Ostadzadeh, S. A., Galuzzi, C., Sima, V. M., Nane, R., & Bertels, K. (2013). ’Quipu: A statistical model for predicting hardware resources ’, ACM Trans. Reconfigurable Technol. Syst. 6(1) .

  18. International Organization for Standardization. ITU-T Recommendation T.81. In ISO/IEC IS 10918-1, http://www.jpeg.org/jpeg/ JPEG homepage (2016).

  19. Tao, Z., Liu, S., & He, J. (2007). A New Algorithm on Short Window MDCT for Dolby AC3, Proceedings of ISPACS.

  20. Zhang, J., Chow, P., & Liu, H (2015). FPGA Implementation of Low-Power and High-PSNR DCT/IDCT Architecture based on Adaptive Recoding CORDIC, International Conference on Field Programmable Technology (FPT).

  21. Gall, D. L. (1991). MPEG: a video compression standard for multimedia applications. Communications of the ACM-Special Issue on Digital Multimedia Systems, 34(4), 46–58.

    Google Scholar 

  22. Xilinx Power Estimator User Guide, UG440 (v2014.1) Xilinx Homepage (2016).

  23. Mehri, H., & Alizadeh, B. (2015). Analytical performance model for FPGA-based reconfigurable computing. Microprocessors and Microsystems, 39, 796–806.

    Article  Google Scholar 

  24. Vivado Design Suite User Guide, Model-Based DSP Design Using System Generator, UG897 (v2015.3) 30, (2015).

Download references

Author information

Authors and Affiliations

  1. Faculté des Sciences de Tunis, Université de Tunis El Manar, LAPER, UR-17-ES11, Campus Universitaire, Tunis, 2092, Tunisia

    Sonia Mami & Imen Ben Saad

  2. ENICarthage, Université de Carthage, Carthage, Tunisia

    Younes Lahbib & Yassine Hachaichi

  3. Electronics and Micro-electronics Laboratory, Université de Monastir, Monastir, Tunisia

    Younes Lahbib

  4. Université de Tunis El Manar, LAMSIN-ENIT, Campus Universitaire, Tunis, 2092, Tunisia

    Yassine Hachaichi

Authors
  1. Sonia Mami
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Imen Ben Saad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Younes Lahbib
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yassine Hachaichi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sonia Mami.

Appendices

Appendix:

Annex 1

This annex gives the details of the PSNR measured considering a jpeg compression chain applyed on Lena, Baboon, Peppers and Goldhill.

Figure 17
figure 17

Unfolded 3π/8 Cordic block for P = 10−2.

Full size image
Figure 18
figure 18

Unfolded π/16 Cordic block for P = 10−2.

Full size image
Figure 19
figure 19

Unfolded 3π/16 Cordic block for P = 10−2.

Full size image
Figure 20
figure 20

Unfolded 3π/8 Cordic block for P = 10−3.

Full size image
Figure 21
figure 21

Unfolded 3π/16 Cordic block for P = 10−3.

Full size image
Figure 22
figure 22

Unfolded π/16 Cordic block for P = 10−3.

Full size image

2.1 Annex 2

This annex gives the detailed implementation of each Cordic block for different angle’s precision degree.

Figure 23
figure 23

Unfolded 3π/8 Cordic block for P = 10−4.

Full size image
Figure 24
figure 24

Unfolded 3π/16 Cordic block for P = 10−4.

Full size image
Figure 25
figure 25

Unfolded π/16 Cordic block for P = 10−4.

Full size image
Figure 26
figure 26

Unfolded 3π/8 Cordic block for P = 10−5.

Full size image
Figure 27
figure 27

Unfolded 3π/16 Cordic block for P = 10−5.

Full size image
Figure 28
figure 28

Unfolded π/16 Cordic block for P = 10−5.

Full size image
Figure 29
figure 29

Unfolded 3π/8 Cordic block for P = 10−6.

Full size image
Figure 30
figure 30

Unfolded 3π/16 Cordic block for P = 10−6.

Full size image
Figure 31
figure 31

Unfolded π/16 Cordic block for P = 10−6.

Full size image
Figure 32
figure 32

Unfolded 3π/8 Cordic block for P = 10−7.

Full size image
Figure 33
figure 33

Unfolded 3π/16 Cordic block for P = 10−7.

Full size image
Figure 34
figure 34

Unfolded π/16 Cordic block for P = 10−7.

Full size image

2.2 Annex 3

This annex gives the detailed values of the power as a function of frequency.

Table 11 The power as a function of frequency for the conventional and the proposed architectures.
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mami, S., Saad, I.B., Lahbib, Y. et al. Enhanced Configurable DCT Cordic Loeffler Architectures for Optimal Power-PSNR Trade-Off. J Sign Process Syst 90, 371–393 (2018). https://doi.org/10.1007/s11265-017-1245-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-017-1245-7

Keywords

Search

Navigation