A novel approach for shape-based object recognition with curvelet transform

  • M. Radhika Mani
  • D. M. Potukuchi
  • Ch. Satyanarayana
Regular Paper


In this work, we revisit multi-resolution analysis (MRA) methods for object recognition. We find an optimal sparse representation of an image using a second-generation Fast Discrete Curvelet Transform (FDCT) and present a novel curvelet approach based on thin plate splines (TPS). Measurement of local deformation at each FDCT coefficient is detailed. Specific deformations in the TPS-based curve-let transformation are identified by minimization (Curvature) of total bending energy. Shape toning is processed through the Euclidean distance. Results of implementation of proposed descriptor for five standard databases are analyzed, while their comparison with other revealed relative efficiency.


Feature vector Shape Object recognition Curvelet transform Thin plate splines 


  1. 1.
    Zhang D, Lu G (2004) Review of shape representation and description techniques. Pattern Recogn 37(1):1–19CrossRefGoogle Scholar
  2. 2.
    Pitas I (2000) Digital image processing, algorithms and application. Wiley, New YorkzbMATHGoogle Scholar
  3. 3.
    Nixon MS, Aguado AS (2002) Feature extraction and image processing, 1st edn. Newnes Publishers, Oxford, pp 247–287CrossRefGoogle Scholar
  4. 4.
    Starck JL, Elad M, Donoho D (2004) Redundant multiscale transforms and their application for morphological component separation. Adv Imaging Electron Phys 132:287–348CrossRefGoogle Scholar
  5. 5.
    Mojsilovic A, Popovic M, Markovic S, Krstic M (1998) Characterization of visually similar diffuse diseases from Bscan liver images using nonseparable wavelet transform. IEEE Trans Med Imaging 17(4):541–549CrossRefGoogle Scholar
  6. 6.
    Alzu’bi S, Amira A (2010) 3D medical volume segmentation using hybrid multiresolution statistical approaches. Adv Artif Intell 2010:1–15CrossRefGoogle Scholar
  7. 7.
    Mulcahy C (1997) Image compression using the Haar wavelet transform. Spelman Sci Math J 1:22–31Google Scholar
  8. 8.
    Fourati W, Kammoun F, Bouhlel MS (2005) Medical image denoising using wavelet thresholding. J Test Eval 33(5):364–369Google Scholar
  9. 9.
    Kara B, Watsuji N (2003) Using wavelets for texture classification. J WSEAS Trans Comput 2(4):920–924Google Scholar
  10. 10.
    Chen GY, Bui TD, Krzyżak A (2009) Invariant pattern recognition using radon, dual-tree complex wavelet and Fourier transforms. Pattern Recogn 42(9):2013–2019CrossRefzbMATHGoogle Scholar
  11. 11.
    Alina B, Ambar D (2013) Performance comparison of cosine, haar, walsh-hadamard, fourier and wavelet transform for shape based image retrieval using fuzzy similarity measure. Proc Technol 10:623–627CrossRefGoogle Scholar
  12. 12.
    Candès E, Demanet L (2005) The curvelet representation of wave propagators is optimally sparse. Commun Pure Appl Math 58(11):1472–1528MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Candès E, Demanet L, Donoho D, Ying L (2006) Fast discrete curvelet transforms. Multiscale Model Simul 5(3):861–899MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Jianwei M, Plonka G (2010) The curvelet transform. IEEE Signal Process Mag 27(2):118–133CrossRefGoogle Scholar
  15. 15.
    Arivazhagan S, Ganesan L, Kumar TGS (2006) Texture classification using curvelet statistical and co-occurrence features, pattern recognition. In: 18th international conference on ICPR 2006, vol 2, pp 938–941Google Scholar
  16. 16.
    Qing-Wu L, Guo-Gao L (2007) eramic microscopic image processing based on fast discrete curvelet transform, Wavelet Analysis and Pattern Recognition. In: ICWAPR ’07. International Conference vol 1, pp 344–349Google Scholar
  17. 17.
    Yungang Z, Lijin G, Wei G, Jun L (2010) ombining color quantization with curvelet transform for image retrieval, Artificial Intelligence and Computational Intelligence (AICI). In: International Conference on vol 1, pp 474–479Google Scholar
  18. 18.
    Chi Z, Hongbin Z (2010) Identifying color image origin using curvelet transform, Image Processing (ICIP). In: 17th IEEE International Conference on, pp 2125–2128Google Scholar
  19. 19.
    Prasad S, Kumar P, Tripathi RC (2011) Plant leaf species identification using Curvelet transform, Computer and Communication Technology (ICCCT). In: 2nd International Conference on, pp 646–652Google Scholar
  20. 20.
    Minhas R, Mohammed AA, Wu QMJ, Sid-Ahmed MA (2011) A robust object detection approach using boosted anisotropic multiresolution analysis, Circuits and Systems (MWSCAS). In: 54th international midwest symposium on IEEE 2011, pp 1–4Google Scholar
  21. 21.
    Esmaeili M, Rabbani H, Dehnavi AM, Dehghani A (2012) Automatic detection of exudates and optic disk in retinal images using curvelet transform. IET Image Proc 6(7):1005–1013Google Scholar
  22. 22.
    Ezekiel S, Alford MG, Ferris D, Jones E, Bubalo A, Gorniak M, Blasch E (2013) Multi-scale decomposition tool for content based image retrieval, applied imagery pattern recognition workshop: sensing for control and augmentation. In: 2013 IEEE (AIPR), pp 1–5Google Scholar
  23. 23.
    Bin H, Islam KK (2013) A comparative analysis of processing periods for strain images generated using 1D spline based approach and 2D thin plate smoothing spline method. In: International conference on informatics, electronics & vision (ICIEV), pp 1–6Google Scholar
  24. 24.
    Candes EJ, Donoho DL (2000) Curvelets—A surprisingly effective non- adaptive representation for objects with edges. Vanderbilt University Press, NashvilleGoogle Scholar
  25. 25.
    Bookstein FL (1991) Morphometric tools for landmark data: geomtery and biology. Cambridge University Press, CambridgeGoogle Scholar
  26. 26.
    Zhang G, Ma ZM, Tong Q, He Y, Zhao T (2008) Shape feature extraction using fourier descriptors with brightness in content based medical image retrieval. In: International conference on intelligent information hiding and multimedia signal processing, pp 71–74Google Scholar
  27. 27.
    Tiagrajah VJ, Razeen AASM (2011) An enhanced shape descriptor based on radial distances. In: IEEE international conference on signal and image processing applications, pp 472–477Google Scholar
  28. 28.
    Sebastian P, Klein T, Kimia B (2004) Computationally efficient wavelet affine invariant functions for shape recognition. IEEE Trans Pattern Anal Mach Intell 26:550–571CrossRefGoogle Scholar
  29. 29.
    Whoi YSK (2000) A region-based shape descriptor using Zernike moments. Signal Process 16:95–102Google Scholar
  30. 30.
    Mokhtarian F, Abbasi F, Kittler J, Smeulders AWM, Jain R (1997) Efficient and robust retrieval by shape content through curvature scale space. Image Databases Multi Media Search 8:51–58Google Scholar
  31. 31.
    Ghazal AE, Basir O, Belkasim S (2009) Farthest point distance: a new shape signature for Fourier descriptors. Sig Process Image Commun 24:572–586CrossRefGoogle Scholar
  32. 32.
    Ghazal AE, Basir O, Belkasim S (2012) Invariant curvature-based Fourier shape descriptors. J Visual Commun Image Represent 23:622–633CrossRefGoogle Scholar
  33. 33.
    Pedrosa Glauco V, Batista Marcos A, Barcelos Celia AZ (2013) Image feature descriptor based on shape salience points. Neuro Comput 23:156–163Google Scholar
  34. 34.
    Mani MR, Varma GPS, Potukuchi DM, Satyanarayana Ch (2015) A conformal mapping based shape signature for object recognition. In: Proceedings of the 15th international conference on applied computer science. Konya, pp 183–187Google Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  • M. Radhika Mani
    • 1
  • D. M. Potukuchi
    • 2
  • Ch. Satyanarayana
    • 3
  1. 1.Department of CSEPragati Engineering CollegeSurampalemIndia
  2. 2.Department of PhysicsJNT University KakinadaKakinadaIndia
  3. 3.Department of CSEJNT University KakinadaKakinadaIndia

Personalised recommendations