Advertisement

Accurate image super-resolution using dense connections and dimension reduction network

  • Shiyu Hu
  • Guodong WangEmail author
  • Yanjie Wang
  • Chenglizhao Chen
  • Zhenkuan Pan
Article
  • 6 Downloads

Abstract

Recently, the convolution neural network (CNN) has achieved significant performance improvements toward the image Super-Resolution (SR) problems. Yet, the existing benchmark arts exist multiple limitations, including make use of the feature information deficiently, accompany with the gradient disappearance phenomenon and have serious time consumption. The paper utilizes a newly designed fully convolutional neural network named Accurate Image Super-resolution Using Dense Connections and Dimension Reduction Network (DCDRN) to fully exploit the image features. Contextual information of image regions utilizes efficiently and accurately through uniting dense connections and cascading small filters multiple times. And such implementation can be regarded as feature extractors to fuse local and global image features. We newly introduce 1 × 1 CNNs parallelization structure in the image reconstruction section to reduce data dimensions of the previous layers, which alleviates the computational burden effectively while avoiding the context info losing. The calculation becomes more complex and the convergence becomes slower during training because of the pre-processed images. The proposed DCDRN invents a simple and effective method which processes the original image directly and the optimization of layers and filters of CNNs shorten the cost of training significantly. Experiments on benchmark datasets with different methods show that DCDRN achieves gratifying performance against state-of-the-art methods. Code is available at https://github.com/doctorwgd/DCDRN .

Keywords

Super-resolution Dense connections Parallelization Contextual information 

Notes

Acknowledgements

This work was supported by the National “Twelfth Five-Year” development plan of science and technology (No.2014BAG03B05) and the National Natural Science Foundation of China (No. 61772294).

References

  1. 1.
    Arbelaez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(5):898–916CrossRefGoogle Scholar
  2. 2.
    Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. In: IEEE Transactions on Neural Networks, pp. 157–166Google Scholar
  3. 3.
    Bevilacqua M, Roumy A, Guillemot C, Alberi M (2012) Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: British Machine Vision Conference, pp. 1–10Google Scholar
  4. 4.
    Dong C, Loy C, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European Conference on Computer Vision, 184–199Google Scholar
  5. 5.
    Dong C, Loy C, He K, Tang X (2015) Image super-resolution using deep convolutional networks. In: TPAMI, pp. 295–307Google Scholar
  6. 6.
    Dong C, Loy C, He K, Tang X (2016) Accelerating the Super-Resolution Convolutional Neural Network. In: European Conference on Computer Vision, pp. 391–407Google Scholar
  7. 7.
    Gao X, Zhang K, Tao D, Li X (2012) Image super-resolution with sparse neighbor embedding. In: IEEE Transactions on Image Processing, pp. 3194–3205Google Scholar
  8. 8.
    He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision, pp.1026–1034Google Scholar
  9. 9.
    He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance. In: ImageNet Classification, pp. 1020–1034Google Scholar
  10. 10.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778Google Scholar
  11. 11.
    Huang J, Singh A, Ahuja N (2015) Single image super-resolution using transformed self-exemplars. In: CVPR, pp 5197–5206Google Scholar
  12. 12.
    Huang G, Sun Y, Liu Z, Sedra D, Weinberger KQ (2016) Deep networks with stochastic depth. In: European Conference on Computer Vision, pp. 646–661Google Scholar
  13. 13.
    Huang G, Liu Z, Laurensvander M, Kilian Q (2017) Densely connected convolutional networks. In: Computer Vision and Pattern Recognition, arXiv:1608.06993Google Scholar
  14. 14.
    Irani M, Peleg S (1991) Improving resolution by image registration. In: Graphical Models and Image Processing, pp. 231–239Google Scholar
  15. 15.
    Kim J, Lee K, Lee M (2016a) Deeply-recursive convolutional network for image super-resolution. In: Computer Vision and Pattern Recognition, pp 1637-1645Google Scholar
  16. 16.
    Kim J, Lee K, Lee M (2016b) Accurate image super-resolution using very deep convolutional networks. In: Computer Vision and Pattern Recognition, pp 1646-1654Google Scholar
  17. 17.
    Larsson G, Maire M, Shakhnarovich G (2017) Ultra-deep neural networks without residuals. In: International Conference on Learning Representations, arXiv:1605.07648Google Scholar
  18. 18.
    LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: IEEE, pp. 2278–2324Google Scholar
  19. 19.
    Li G, Wu Q, Qiu L, Huang X (2018) Image super-resolution using a dilated convolutional neural network. Neurocomputing, 1219–1230Google Scholar
  20. 20.
    Li S, Ren F, Lei G, Yue G, Hou C (2018) A two-channel convolutional neural network for image super-resolution. Neurocomputing 275:267–277CrossRefGoogle Scholar
  21. 21.
    Lin M, Chen Q, Yan S (2014) Network in network. In: International Conference on Learning Representations, arXiv:1312.4400Google Scholar
  22. 22.
    Liu S, Wu X (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. In: TIPGoogle Scholar
  23. 23.
    Liu S, Lu MY, Liu GC, Pan Z (2017) A novel distance metric: generalized relative entropy. Entropy 19(6):269CrossRefGoogle Scholar
  24. 24.
    Liu S, Pan Z, Song HB (2017) Digital image watermarking method based on DCT and fractal encoding. In: IET Image Processing, pp.815–821Google Scholar
  25. 25.
    Liu S, Bai WL, Liu GC, Li WH, Srivastava M (2018) Parallel fractal compression method for big video data. Complexity 2016976Google Scholar
  26. 26.
    Liu G, Liu S, Muhammad K, Kumar A (2018) Object tracking in vary lighting conditions for fog based intelligent surveillance of public spaces. In: IEEE Access, pp. 29283–29296Google Scholar
  27. 27.
    Mao X, Shen J, Yang Y (2016a) Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Neural Information Processing Systems, pp. 2802–2810Google Scholar
  28. 28.
    Mao X, Shen C, Yang Y (2016b) Image restoration using convolutional auto-encoders with symmetric skip connections. In: Proceedings of the Neural Information Processing Systems, arXiv:1606.08921Google Scholar
  29. 29.
    Martin D, Fowlkes C, Tal D, Malik J (2001) A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: International Conference on Computer Vision, volume 2, pp. 416–423Google Scholar
  30. 30.
    Pan Z, Liu S, Fu W (2016) A review of visual moving target tracking. Multimedia Tools and Applications, pp. 16989–17018Google Scholar
  31. 31.
    Romano Y, Isidoro J, Milanfar P (2017) Rapid and accurate image super resolution. IEEE Transactions on Computational Imaging 3:110–125MathSciNetCrossRefGoogle Scholar
  32. 32.
    Salvador J, Pérez-Pellitero E (2015) Naive Bayes super-resolution forest. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 325–333Google Scholar
  33. 33.
    Schulter S, Leistner C, Bischof H (2015) Fast and accurate image upscaling with super-resolution forests. In: CVPR, pp. 3791–3799Google Scholar
  34. 34.
    Srivastava RK, Greff K, Schmidhuber J (2015) Training very deep networks. In: Advances in Neural Information Processing Systems, pp. 2377–2385Google Scholar
  35. 35.
    Thom M, Schweiger R, Palm G, Rothermel A (2013) Learning convolutional neural networks from few samples. In: International Symposium on Neural Networks, pp 1884–1890Google Scholar
  36. 36.
    Timofte R, DeSmet V, VanGool L (2014) Adjusted anchored neighborhood regression for fast super-resolution. In: ACCV, pp. 111–126Google Scholar
  37. 37.
    Tu WQ, Pop F, Jia W, Wu J, Iacono M (2018) Visual attention feature (VAF): a novel strategy for visual tracking based on cloud platform in intelligent surveillance systems. Journal of Parallel and Distributed Computing, pp. 182–194Google Scholar
  38. 38.
    Yamanaka J, Kuwashima S, Kurita T (2017) Fast and accurate image super resolution by deep CNN with skip connection and network in network. In: Computer Vision and Pattern Recognition, arXiv:1707.05425Google Scholar
  39. 39.
    Yang J, Wright J, Huang T, Ma Y (2010) Image super resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873MathSciNetCrossRefGoogle Scholar
  40. 40.
    Yang J, Wang Z, Lin Z, Cohen S, Huang T (2012) Coupled dictionary training for image super-resolution. In: IEEE Transactions on Image Processing, pp. 3467–3478Google Scholar
  41. 41.
    Yang C, Ma C, Yang M (2014) Single-image super-resolution: a benchmark. In: European Conference on Computer Vision, pp. 372–386Google Scholar
  42. 42.
    Zeiler MD, Krishnan D, Taylor GW, Fergus R (2010) Deconvolutional networks. In: Computer Vision and Pattern Recognition, pp. 2528–2535Google Scholar
  43. 43.
    Zeyde R, Elad M, Protter M (2012) On single image scale-up using sparse-representations. In: International Conference on Curves and Surfaces, pp. 711–730Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Shiyu Hu
    • 1
  • Guodong Wang
    • 1
    Email author
  • Yanjie Wang
    • 1
  • Chenglizhao Chen
    • 1
  • Zhenkuan Pan
    • 1
  1. 1.College of Computer Science and TechnologyQingdao UniversityQingdaoPeople’s Republic of China

Personalised recommendations