Advertisement

An efficient framework for increasing image quality using DRN Bi-layer enfolded compressor

  • 11 Accesses

Abstract

Lossy /lossless image compression technique results will either improve the quality of image with reduced compression ratio or degrades the image with better compression ratio. But on dealing with the combined lossy/lossless techniques, they provide the output with better image quality and high compression rate, however, the techniques failed to obtain better efficiency due to less predictive nature. Hence, to acquire an image having better compression rate with improved predictive nature, a novel framework is introduced in our proposed work. It uses a Deep Residual Network Bi-Layer Enfolded Compressor (DRN-BLEC) to enhance the image quality. In order to obtain better compression rate, the Mexican Meyer Hat Wavelet Transform (MMHWT) is used. Similarly, the well knowledge quantization is achieved by utilizing DRN for learning; it is then followed by the Lloyds quantization technique that groups the feature values by quantizing it, which in turn boost-up the resolution of the image. Consequently with DRN, the process of encoding and decoding doesn’t requires to be done separately since two residual layer of the DRN are trained to encode and decode the images, which thereby reduces the time required for compression process. Thus a compressed image with high resolution is obtained without redundancy, moreover with high compression ratio. The architecture of the DRN-BLEC is implemented in MATLAB and the respective result structure is validated.

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

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 199

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

References

  1. 1.

    Agustsson E, Timofte R (2017) Ntire 2017 challenge on single image super-resolution: dataset and study. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 126–135

  2. 2.

    Agustsson E, Mentzer F, Tschannen M, Cavigelli L, Timofte R, Benin L, Gool LV (2017) Soft-to-hard vector quantization for end-to-end learning compressible representations. In: Advances in neural information processing systems, pp 1141–1151

  3. 3.

    Ahn N, Kang B, Sohn KA (2018) Fast, accurate, and lightweight super-resolution with cascading residual network. In: Proceedings of the European conference on computer vision (ECCV), pp 252–268

  4. 4.

    Balle J, Laparra V, Simoncelli EP (2016) End-to-end optimized image compression. arXiv preprint arXiv:1611.01704

  5. 5.

    Chen Q, Yang J, Gou J (2005) Image compression method using improved PSO vector quantization. Springer- Verlag, Berlin Heidelberg, pp 490–495

  6. 6.

    Cheng J, Wu J, Leng C, Wang Y, Hu Q (2017) Quantized CNN: a unified approach to accelerate and compress convolutional networks. IEEE Trans Neural Netw Learn Syst 99:1–14

  7. 7.

    Courbariaux M, Bengio Y, David JP (2015) Binary connect: training deep neural networks with binary weights during propagations. In: Advances in neural information processing systems (NIPS), pp 3123–3131

  8. 8.

    Devore RA, Jawerth B, Lucier BJ (1992) Image compression through wavelet transform coding. IEEE Trans Inf Theory 38(2):719–746

  9. 9.

    Fan Y, Yu J, Huang TS (2018) Wide-activated deep residual networks based restoration for BPG-compressed images. In: Proc. IEEE conf. comput. vis. pattern recognit. workshops pp 2621–2624

  10. 10.

    Gaidhane VH, Singh V, Hote YV, Kumar M (2011) New approaches for image compression using neural network. J Intell Learn Syst Appl 3(04):220

  11. 11.

    Ginesu G, Pintus M, Giusto DD (2012) Objective assessment of the WebP image coding algorithm. Signal Process Image Commun 27(8):867–874

  12. 12.

    He K, Wang R, Tao D, Cheng J, Liu W (2018) Color transfer pulse-coupled neural networks for underwater robotic visual systems. IEEE Access 6:32850–32860

  13. 13.

    Hou W, Gao X, Tao D, Li X (2015) Blind image quality assessment via deep learning. IEEE Transactions on Neural Networks and Learning Systems 26(6):1275–1286

  14. 14.

    Hui Z, Wang X, Gao X (2018) Fast and accurate single image super-resolution via information distillation network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 723–731

  15. 15.

    Kundu D, Evans BL (2015) Full-reference visual quality assessment for synthetic images: a subjective study. In: 2015 IEEE international conference on image processing (ICIP), IEEE, pp 2374–2378

  16. 16.

    Li M, Zuo W, Gu S, Zhao D, Zhang D (2017) Learning convolutional networks for content-weighted image compression. arXiv preprint arXiv:1703.10553

  17. 17.

    Li H, He X, Tao D, Tang Y, Wang R (2018) Joint medical image fusion, denoising and enhancement via discriminative low-rank sparse dictionaries learning. Pattern Recogn 79:130–146

  18. 18.

    Mi X, Ren H, Ouyang Z, Wei W, Ma K (2005) The use of the Mexican hat and the Morlet wavelets for detection of ecological patterns. Plant Ecol 179(1):1–19

  19. 19.

    Nguyen T, Marpe D (2015) Objective performance evaluation of the HEVC main still picture profile. IEEE Trans Circuits Syst Video Technol 25(5):790–797

  20. 20.

    Peng F, Qin L, Long M (2016) POSTER: non-intrusive face spoofing detection based on guided filtering and image quality analysis. In: International conference on security and privacy in communication systems, Springer, Cham, pp 774–777

  21. 21.

    Prakash A, Moran N, Garber S, DiLillo A, Storer J (2017) Semantic perceptual image compression using deep convolution networks. In: 2017 data compression conference (DCC), IEEE, pp 250–259

  22. 22.

    Rein A, Fitzek FH, Gühmann C, Sikora T (2015) Evaluation of the wavelet image two-line coder: a low complexity scheme for image compression. Signal Process Image Commun 37:58–74

  23. 23.

    Ruiz D, Fernández-Escribano G, Martínez JL, Cuenca P (2016) Fast intra mode decision algorithm based on texture orientation detection in HEVC. Signal Process Image Commun 44:12–28

  24. 24.

    Sulavko AE, Volkov DA, Zhumazhanova SS, Borisov RV (2018) Subjects authentication based on secret biometric patterns using wavelet analysis and flexible neural networks. In: 2018 XIV international scientific-technical conference on actual problems of electronics instrument engineering (APEIE), pp 218–227

  25. 25.

    Tai Y, Yang J, Liu X (2017) Image super-resolution via deep recursive residual network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3147–3155

  26. 26.

    Tang CW, Hang HM (2003) A feature-based robust digital image watermarking scheme. IEEE Trans Signal Process 51:950–959

  27. 27.

    Tao D, Guo Y, Yu B, Pang J, Yu Z (2017) Deep multi-view feature learning for person re-identification. IEEE Trans Circuits Syst Video Technol 28(10):2657–2666

  28. 28.

    Theis L, Shi W, Cunningham A, Huszar F (2017) Lossy image compression with compressive autoencoders, arXiv preprint arXiv: 1703.00395

  29. 29.

    Toderici G, O’Malley SM, Hwang SJ, Vincent D, Minnen D, Baluja S, Covell M, Sukthankar R. (2015) Variable rate image compression with recurrent neural networks. arXiv preprint arXiv: 1511.06085

  30. 30.

    Toderici G, Vincent D, Johnston N, Hwang SJ, Minnen D, Shor J, Covell M. (2017) Full resolution image compression with recurrent neural networks. In: Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on, pp 5435–5443

  31. 31.

    Torfason R, Mentzer F, Agustsson E, Tschannen M, Timofte R, Van Gool L (2018) Towards image understanding from deep compression without decoding. arXiv preprint arXiv:1803.06131

  32. 32.

    Wang J, Zhang F (2010) Study of the image compression based on SPHIT algorithm. In: IEEE international conference on intelligent computing and cognitive informatics pp 130–133

  33. 33.

    Wang Y, Shen J, Zhang J (2018) Deep Bi-Dense networks for image super-resolution. In: 2018 digital image computing: techniques and applications (DICTA), pp 1–8

  34. 34.

    Wei Y, Yuan Q, Shen H, Zhang L (2017) Boosting the accuracy of multispectral image pansharpening by learning a deep residual network. IEEE Geosci Remote Sens Lett 14:1795–1799

  35. 35.

    Wu S, Zhong S, Liu Y (2018) Deep residual learning for image steganalysis. Multimed Tools Appl 77:10437–10453

  36. 36.

    Xu F, Yan Z, Xiao G, Zhang K, Zuo W (2018) JPEG image super-resolution via deep residual network. In: International conference on intelligent computing, pp 472–483

  37. 37.

    Yao Y, Li X, Lu Y (2016) Fast intra mode decision algorithm for HEVC based on dominant edge assent distribution. Multimed Tools Appl 75(4):1963–1981

  38. 38.

    Zhong Z, Li J, Luo Z, Chapman M (2018) Spectral–spatial residual network for hyper spectral image classification: a 3-D deep learning framework. IEEE Trans Geosci Remote Sens 56:847–858

Download references

Author information

Correspondence to S. Tamboli Shabanam.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Shabanam, S.T., Udupi, V.R. & Subudhi, B.N. An efficient framework for increasing image quality using DRN Bi-layer enfolded compressor. Multimed Tools Appl (2020) doi:10.1007/s11042-019-08227-3

Download citation

Keywords

  • DRN Bi-layer enfolded compressor
  • Lloyd’s quantization
  • Deep residual network
  • Lossless compression
  • Lossy compression