Gradient-Guided DCNN for Inverse Halftoning and Image Expanding

  • Yi Xiao
  • Chao Pan
  • Yan ZhengEmail author
  • Xianyi Zhu
  • Zheng Qin
  • Jin Yuan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11364)


Inverse halftoning and image expanding refer to the ill-posed problems which restore higher-bit images from lower bit ones. Many scholars have studied these problems so far, but the restored images still suffer either quantization artifacts or fine detail losses. Although recent deep convolutional neural network (DCNN) based methods have shown its advantage in these two problems, it is hard to restore high quality images with fine details if no extra information is feeded to the network. To solve this problem, this paper proposes a gradient-guided DCNN model for inverse halftoning and image expanding. The DCNN model consists of two stages. In the first stage, two subnetworks are designed to explicitly predict the gradient maps of the input image, which account for the detail information of image. In the second stage, the gradient maps, concatenated with the input image, are feeded to another subnetwork to guide the reconstruction of the final results. Experimental results show that our method outperforms the state-of-arts in terms of both visual quality and numerical evaluation. In particular, our method better recovers the fine details of the images.


Gradient-guided Inverse halftoning Image expanding 


  1. 1.
    Bayer, B.E.: An optimal method for two-level rendition of continuous-tone pictures. In: International Conference on Communications (1973)Google Scholar
  2. 2.
    Bhooshan, S., Kumar, V.: 2D T-law: a novel approach for image companding (2010)Google Scholar
  3. 3.
    Bozkurt, G., Cetin, A.E.: Restoration of error-diffused images using POCS. In: 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 3225–3228 (1999)Google Scholar
  4. 4.
    Catté, F., Lions, P.L., Morel, J.M., Coll, T.: Image selective smoothing and edge detection by nonlinear diffusion. SIAM J. Numer. Anal. 29(1), 182–193 (1992). Scholar
  5. 5.
    Eschbach, R., Knox, K.T.: Error-diffusion algorithm with edge enhancement. J. Opt. Soc. Am. A 8(12), 1844–1850 (1991)CrossRefGoogle Scholar
  6. 6.
    Floyd, R.W.: An adaptive algorithm for spatial grayscale. In: Proceedings of Society Information Display, vol. 17, pp. 75–77 (1976)Google Scholar
  7. 7.
    Hein, S., Zakhor, A.: Halftone to continuous-tone conversion of error-diffusion coded images. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 4(2), 208–16 (1995)CrossRefGoogle Scholar
  8. 8.
    Hou, X., Qiu, G.: Image companding and inverse halftoning using deep convolutional neural networks. CoRR abs/1707.00116 (2017)Google Scholar
  9. 9.
    Huang, W.B., Chang, W.C., Lu, Y.W., Su, A.W.Y., Kuo, Y.H.: Halftone/contone conversion using neural networks. In: 2004 International Conference on Image Processing, ICIP 2004, vol. 5, pp. 3547–3550, October 2004.
  10. 10.
    Huang, W.B., Su, A.W.Y., Kuo, Y.H.: Neural network based method for image halftoning and inverse halftoning. Expert Syst. Appl. 34(4), 2491–2501 (2008)CrossRefGoogle Scholar
  11. 11.
    Jarvis, J., Roberts, C.: A new technique for displaying continuous tone images on a bilevel display. IEEE Trans. Commun. 24(8), 891–898 (1976). Scholar
  12. 12.
    Mulligan, J.B., Ahumada, J.A.: Principled halftoning based on human vision models (1992).
  13. 13.
    Kang, H.R.: Digital Color Halftoning. Society of Photo-Optical Instrumentation Engineers. SPIE, Bellingham (1999)Google Scholar
  14. 14.
    Kim, S.H., Allebach, J.P.: Impact of HVS models on model-based halftoning. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 11(3), 258–69 (2002)CrossRefGoogle Scholar
  15. 15.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. Computer Science (2014)Google Scholar
  16. 16.
    Kite, T.D., Damera-Venkata, N., Evans, B.L., Bovik, A.C.: A fast, high-quality inverse halftoning algorithm for error diffused halftones. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 9(9), 1583–92 (2000)CrossRefGoogle Scholar
  17. 17.
    Larson, G.W., Rushmeier, H., Piatko, C.: A visibility matching tone reproduction operator for high dynamic range scenes. IEEE Trans. Vis. 3(4), 291–306 (1997)Google Scholar
  18. 18.
    Li, P., Allebach, J.P.: Look-up-table based halftoning algorithm. IEEE Trans. Image Process. 9(9), 1593–1603 (2000)CrossRefGoogle Scholar
  19. 19.
    Li, Y., Huang, J.-B., Ahuja, N., Yang, M.-H.: Deep joint image filtering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 154–169. Springer, Cham (2016). Scholar
  20. 20.
    Li, Y., Sharan, L., Adelson, E.H.: Compressing and companding high dynamic range images with subband architectures. ACM Trans. Graph. 24(3), 836–844 (2005). Scholar
  21. 21.
    Lin, T., et al.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014).
  22. 22.
    Mese, M., Vaidyanathan, P.P.: Look-up table (LUT) method for inverse halftoning. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 10(10), 1566–78 (2001)CrossRefGoogle Scholar
  23. 23.
    Mese, M., Vaidyanathan, P.P.: Tree-structured method for LUT inverse halftoning and for image halftoning. IEEE Trans. on Image Process. 11, 644–655 (2002)CrossRefGoogle Scholar
  24. 24.
    Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR abs/1411.1784 (2014).
  25. 25.
    Pelcastre-Jimenez, F., Nakano-Miyatake, M., Toscano-Medina, K., Sanchez-Perez, G., Perez-Meana, H.: An inverse halftoning algorithm based on neural networks and UP(x) atomic function. In: International Conference on Telecommunications and Signal Processing, pp. 523–527 (2015)Google Scholar
  26. 26.
    Neelamani, R., Nowak, R.D., Baraniuk, R.G.: WInHD: wavelet-based inverse halftoning via deconvolution. IEEE Trans. Image Process. (2002)Google Scholar
  27. 27.
    Saika, Y., Inoue, J.I., Tanaka, H., Okada, M.: Bayes-optimal solution to inverse halftoning based on statistical mechanics of the Q-ising model. Central Eur. J. Phys. 7(3), 444–456 (2009)Google Scholar
  28. 28.
    Stevenson, R.L.: Inverse halftoning via map estimation. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 6(4), 574 (1997)CrossRefGoogle Scholar
  29. 29.
    Sullivan, J.R., Ray, L.A., Miller, R.: Design of minimum visual modulation halftone patterns. IEEE Trans. Syst. Man Cybern. 21(1), 33–38 (1991). Scholar
  30. 30.
    Thao, N.T.: Set theoretic inverse halftoning. In: Proceedings of International Conference on Image Processing, vol. 1, pp. 783–786 (1997)Google Scholar
  31. 31.
    Tumblin, J., Rushmeier, H.: Tone reproduction for realistic images. Comput. Graph. 13(6), 42–48 (1993)CrossRefGoogle Scholar
  32. 32.
    Unal, G.B., Cetin, A.E.: Restoration of error-diffused images using projection onto convex sets. IEEE Trans. Image Process. 10, 1836–1841 (2001)CrossRefGoogle Scholar
  33. 33.
    Wang, L., Hua, B.-S., Li, X.: Adaptive energy diffusion for blind inverse halftoning. In: Qiu, G., Lam, K.M., Kiya, H., Xue, X.-Y., Kuo, C.-C.J., Lew, M.S. (eds.) PCM 2010. LNCS, vol. 6297, pp. 470–480. Springer, Heidelberg (2010). Scholar
  34. 34.
    Wen, Z.Q., Lu, Y.L., Zeng, Z.G., Zhu, W.Q., Ai, J.H.: Optimizing template for lookup-table inverse halftoning using elitist genetic algorithm, January 2015Google Scholar
  35. 35.
    Xiao, Y., Pan, C., Xianyi Zhu, H.J., Zheng, Y.: Deep neural inverse halftoning. In: International Conference on Virtual Reality and Visualization (ICVRV 2017) (2017, to appear)Google Scholar
  36. 36.
    Xiong, Z., Orchard, M.T., Ramchandran, K.: Inverse halftoning using wavelets. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 8(10), 1479–83 (1999)CrossRefGoogle Scholar
  37. 37.
    Yang, B., Schmucker, M., Funk, W., Busch, C., Sun, S.: Integer DCT-based reversible watermarking for images using companding technique. In: Proceedings of SPIE - The International Society for Optical Engineering, vol. 5306, pp. 405–415 (2004)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yi Xiao
    • 1
  • Chao Pan
    • 1
  • Yan Zheng
    • 2
    Email author
  • Xianyi Zhu
    • 1
  • Zheng Qin
    • 1
  • Jin Yuan
    • 1
  1. 1.College of Computer Science and Electronic EngineeringHunan UniversityChangshaChina
  2. 2.College of Electrical and Information EngineeringHunan UniversityChangshaChina

Personalised recommendations