access icon free Inverse texture synthesis in wavelet packet trees

Inverse texture synthesis (ITS) plays an important role in many computer vision applications. It aims at generating small compaction images to capture significant features of textures, from which arbitrarily large images with similar textures can be re-synthesised. This study presents a fast approach to ITS with two algorithms developed in hierarchical wavelet packet (WP) trees: the modified inverse texture synthesis (MITS) algorithm, which extends the ITS algorithm into the WP domain, and the wavelet-packet-tree-based cropping (WPTC) algorithm for the initialisation of MITS. Experimental results show that the combination of WPTC and MITS termed the image compaction in wavelet packet trees algorithm outperforms the ITS algorithm in terms of the ‘peak signal-to-noise ratio’ and computation time.

Inspec keywords: computer vision; feature extraction; image texture

Other keywords: hierarchical wavelet packet; MITS algorithm; computer vision applications; image compaction; WPTC algorithm; modified inverse texture synthesis; wavelet packet trees algorithm; wavelet packet tree based cropping; WP trees; peak signal-to-noise ratio; texture features

Subjects: Optical, image and video signal processing; Computer vision and image processing techniques

References

    1. 1)
      • 16. Abbate, A., DeCusatis, C., Das, P.K.: ‘Wavelets and subbands’ (Springer, 2002).
    2. 2)
      • 19. Hsin, H.C., Sung, T.Y., Shieh, Y.S., Cattani, C.: ‘A new texture synthesis algorithm based on wavelet packet tree’, Math. Probl. Eng., 2012, 2012, 12pp, doi: 10.1155/2012/305384.
    3. 3)
    4. 4)
      • 11. Wei, L.Y., Levoy, M.: ‘Fast texture synthesis using tree-structured vector quantization’. ACM SIGGRAPH, 2000, pp. 479488.
    5. 5)
      • 2. Wei, L.Y., Levoy, M.: ‘Order independent texture synthesis’. Stanford Computer Science TR-2002-01, 2002.
    6. 6)
      • 1. Wei, L.Y., Lefebvre, S., Kwatra, V., Turk, G.: ‘State of the art in example-based texture synthesis’. Eurographics '09 State of the Art Reports (STARs), Eurographics, March2009.
    7. 7)
      • 10. De Bonet, J.S.: ‘Multiresolution sampling procedure for analysis and synthesis of texture images’. ACM SIGGRAPH, 1997, pp. 361368.
    8. 8)
      • 4. Ffros, A.A., Freeman, W.T.: ‘Image quilting for texture synthesis and transfer’. Proc. SIGGRAPH, 2001, pp. 341346.
    9. 9)
      • 3. Cheng, G., Dong, J.: ‘Seamless montage of natural texture’. Third Int. Conf. on Advanced Computer Control (ICACC 2011), 2011, pp. 4851.
    10. 10)
      • 17. Yu, Y., Luo, J., Chen, C.W.: ‘Multiresolution block sampling based method for texture synthesis’. 16th Int. Conf. Pattern Recognition, 2002, pp. 239242.
    11. 11)
      • 20. Juang, Y.S., Hsin, H.C., Sung, T.Y., Cattani, C.: ‘Fast texture synthesis in adaptive wavelet packet trees’, Math. Probl. Eng., 2013, 2013, Article ID 416186 (8pp).
    12. 12)
      • 12. Wei, L.Y., Han, J., Zhou, K., Bao, H., Guo, B., Shum, H.Y.: ‘Inverse texture synthesis’. SIGGRAPH 2008, 2008, 14pp.
    13. 13)
      • 18. Cui, H.F., Zheng, X., Ruan, T.: ‘An efficient texture synthesis algorithm based on WT’. Proc. Seventh IEEE Int. Conf. Machine Learning and Cybernetics, 2008, pp. 34723477.
    14. 14)
      • 6. Li, S.Z.: ‘Markov random field modeling in image analysis’ (Springer, 2009).
    15. 15)
      • 7. Efros, A.A., Leung, T.K.: ‘Texture synthesis by non-parametric sampling’. Proc. Seventh IEEE Int. Conf. Computer Vision (ICCV 99), 1999, pp. 10331038.
    16. 16)
      • 8. Kwatra, V., Essa, I., Bobick, A., Kwatra, N.: ‘Texture optimization for example-based synthesis’. SIGGRAPH'05, 2005, pp. 795802.
    17. 17)
    18. 18)
    19. 19)
      • 21. Available: http://graphics.stanford.edu/projects/texture/demo/.
    20. 20)
    21. 21)
      • 15. Goswami, J.C., Chan, A.K.: ‘Fundamentals of wavelets: theory, algorithm, and applications’ (John Wiley & Sons, 2011).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0262
Loading

Related content

content/journals/10.1049/iet-cvi.2013.0262
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading