Abstract
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
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Krotkov, E.P.: Focusing. International Journal of Computer Vision 1(3), 223–237 (1987)
Nair, H.N., Stewart, C.V.: Robust Focus Ranging. In: IEEE Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, pp. 309–314 (1992)
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)
Grossmann, P.: Depth from Focus. Pattern Recognition Letters 5(1), 63–69 (1987)
Pentland, A.P.: A New Sense for Depth of Field. IEEE Transaction on Pattern Analysis and Machine Intelligence 9(4), 523–531 (1987)
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)
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)
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)
Subbarao, M., Surya, G.: Depth from Defocus: A Spatial Domain Approach. International Journal on Computer Vision 13(3), 271–294 (1994)
Xu, S., Capson, D.W., Caelli, T.M.: Range Measurement from Defocus Gradient. Machine Vision Applications 8, 179–186 (1995)
Asada, N., Fujiwara, H., Matsuyama, T.: Edge and depth from focus. International Journal on Computer Vision 26(2), 153–163 (1998)
Watanabe, M., Nayar, S.K.: Rational filters for passive depth from defocus. International Journal on Computer Vision 27(3), 203–225 (1998)
Asada, N., Fujiwara, H., Matsuyama, T.: Particle depth measurement based on depth-from-defocus. Optics & Laser Technology 31(1), 95–102 (1999)
Chaudhuri, S., Rajagopalan, A.N.: Depth from defocus: A real aperture imaging approach. Springer, New York (1999)
Pham, D.T., Aslantas, V.: Depth from defocusing using a neural network. Pattern Recognition 32(5), 715–727 (1999)
Asif, M., Choi, T.S.: Shape from focus using multilayer feedforward neural networks. IEEE Transaction on Image Processing 10(11), 1670–1675 (2001)
Aslantas, V.: Depth from automatic defocusing (in publication)
Aslantas, V., Tunckanat, M.: Depth From Image Sharpness Using a Neural Network. In: ICSP, Çanakkale, Turkey, pp. 260–265 (2003)
Aslantas, V.: Estimation of Depth From Defocusing Using A Neural Network. In: ICIS International Conference on Signal Processing, Çanakkale, Turkey, pp. 305–309 (2003)
Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge (1986)
Horn, B.K.P.: Robot Vision. McGraw-Hill, New York (1986)
Gill, P.E., Murray, W., Wright, H.: Practical Optimization. Academic Press, New York (1981)
Wei, C.: Three Dimensional Machine Vision Using Image Defocus, Ph.D. Dissertation, Electrical Eng., State University of New York at Stony Brook (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Aslantas, V., Tunckanat, M. (2006). Depth of General Scenes from Defocused Images Using Multilayer Feedforward Networks. In: Savacı, F.A. (eds) Artificial Intelligence and Neural Networks. TAINN 2005. Lecture Notes in Computer Science(), vol 3949. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11803089_5
Download citation
DOI: https://doi.org/10.1007/11803089_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36713-0
Online ISBN: 978-3-540-36861-8
eBook Packages: Computer ScienceComputer Science (R0)