Depth of General Scenes from Defocused Images Using Multilayer Feedforward Networks

  • Veysel Aslantas
  • Mehmet Tunckanat
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3949)


One of the important tasks in computer vision is the computation of object depth from acquired images. This paper explains the use of neural networks to calculate the depth of general objects using only two images, one of them being a focused image and the other one a blurred image. Having computed the power spectra of each image, they are divided to obtain a result which is independent from the image content. The result is then used for training Multi-Layer Perceptron (MLP) neural network (NN) trained by the backpropagation algorithm to determine the distance of the object from the camera lens. Experimental results are presented to validate the proposed approach


Spread Parameter Convolution Operation Focus Image Sensor Plane Optical Transfer Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Krotkov, E.P.: Focusing. International Journal of Computer Vision 1(3), 223–237 (1987)CrossRefGoogle Scholar
  2. 2.
    Nair, H.N., Stewart, C.V.: Robust Focus Ranging. In: IEEE Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, pp. 309–314 (1992)Google Scholar
  3. 3.
    Subbarao, M., Choi, T.: Accurate Recovery of Three Dimensional Shape from Focus. IEEE Transaction on Pattern Analysis and Machine Intelligence 17(3), 266–274 (1995)CrossRefGoogle Scholar
  4. 4.
    Grossmann, P.: Depth from Focus. Pattern Recognition Letters 5(1), 63–69 (1987)CrossRefGoogle Scholar
  5. 5.
    Pentland, A.P.: A New Sense for Depth of Field. IEEE Transaction on Pattern Analysis and Machine Intelligence 9(4), 523–531 (1987)CrossRefGoogle Scholar
  6. 6.
    Subbarao, M., Gurumoorthy, N.: Depth Recovery from Blurred Edges. In: IEEE Conference on Computer Vision and Pattern Recognition, Ann Arbor, Michigan, pp. 498–503 (1988)Google Scholar
  7. 7.
    Holeva, L.F.: Range Estimation from Camera Blur by Regularised Adaptive Identification. International Journal on Pattern Recognition and Artificial Intelligence 8(6), 1273–1300 (1994)CrossRefGoogle Scholar
  8. 8.
    Pentland, A.P., Scherock, S., Darrell, T., Girod, B.: Simple Range Cameras based on Focal Error. Journal of Optical Society of America 11(11), 2925–2934 (1994)CrossRefGoogle Scholar
  9. 9.
    Subbarao, M., Surya, G.: Depth from Defocus: A Spatial Domain Approach. International Journal on Computer Vision 13(3), 271–294 (1994)CrossRefGoogle Scholar
  10. 10.
    Xu, S., Capson, D.W., Caelli, T.M.: Range Measurement from Defocus Gradient. Machine Vision Applications 8, 179–186 (1995)CrossRefGoogle Scholar
  11. 11.
    Asada, N., Fujiwara, H., Matsuyama, T.: Edge and depth from focus. International Journal on Computer Vision 26(2), 153–163 (1998)CrossRefGoogle Scholar
  12. 12.
    Watanabe, M., Nayar, S.K.: Rational filters for passive depth from defocus. International Journal on Computer Vision 27(3), 203–225 (1998)CrossRefGoogle Scholar
  13. 13.
    Asada, N., Fujiwara, H., Matsuyama, T.: Particle depth measurement based on depth-from-defocus. Optics & Laser Technology 31(1), 95–102 (1999)CrossRefGoogle Scholar
  14. 14.
    Chaudhuri, S., Rajagopalan, A.N.: Depth from defocus: A real aperture imaging approach. Springer, New York (1999)CrossRefGoogle Scholar
  15. 15.
    Pham, D.T., Aslantas, V.: Depth from defocusing using a neural network. Pattern Recognition 32(5), 715–727 (1999)CrossRefGoogle Scholar
  16. 16.
    Asif, M., Choi, T.S.: Shape from focus using multilayer feedforward neural networks. IEEE Transaction on Image Processing 10(11), 1670–1675 (2001)CrossRefMATHGoogle Scholar
  17. 17.
    Aslantas, V.: Depth from automatic defocusing (in publication)Google Scholar
  18. 18.
    Aslantas, V., Tunckanat, M.: Depth From Image Sharpness Using a Neural Network. In: ICSP, Çanakkale, Turkey, pp. 260–265 (2003)Google Scholar
  19. 19.
    Aslantas, V.: Estimation of Depth From Defocusing Using A Neural Network. In: ICIS International Conference on Signal Processing, Çanakkale, Turkey, pp. 305–309 (2003)Google Scholar
  20. 20.
    Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge (1986)Google Scholar
  21. 21.
    Horn, B.K.P.: Robot Vision. McGraw-Hill, New York (1986)Google Scholar
  22. 22.
    Gill, P.E., Murray, W., Wright, H.: Practical Optimization. Academic Press, New York (1981)MATHGoogle Scholar
  23. 23.
    Wei, C.: Three Dimensional Machine Vision Using Image Defocus, Ph.D. Dissertation, Electrical Eng., State University of New York at Stony Brook (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Veysel Aslantas
    • 1
  • Mehmet Tunckanat
    • 1
  1. 1.Faculty of Engineering, Department of Computer Eng.Erciyes UniversityMelikgazi, KayseriTurkey

Personalised recommendations