Browse > Article

3D Shape Recovery from Image Focus using Gaussian Process Regression  

Mahmood, Muhammad Tariq (Korea University of Technology and Education, School of Computer Science and Engineering)
Choi, Young Kyu (Korea University of Technology and Education, School of Computer Science and Engineering)
Publication Information
Journal of the Semiconductor & Display Technology / v.11, no.3, 2012 , pp. 19-25 More about this Journal
Abstract
The accuracy of Shape From Focus (SFF) technique depends on the quality of the focus measurements which are computed through a focus measure operator. In this paper, we introduce a new approach to estimate 3D shape of an object based on Gaussian process regression. First, initial depth is estimated by applying a conventional focus measure on image sequence and maximizing it in the optical direction. In second step, input feature vectors consisting of eginvalues are computed from 3D neighborhood around the initial depth. Finally, by utilizing these features, a latent function is developed through Gaussian process regression to estimate accurate depth. The proposed approach takes advantages of the multivariate statistical features and covariance function. The proposed method is tested by using image sequences of various objects. Experimental results demonstrate the efficacy of the proposed scheme.
Keywords
Depth recovery; Shape From Focus; Focus Measure; Gaussian Process; Regression;
Citations & Related Records
연도 인용수 순위
  • Reference
1 M. Subbarao and T. S. Choi, "Accurate recovery of three-dimensional shape from image focus," IEEE Transactions on pattern analysis and machine intelligence, vol. 17, pp. 266 - 274, 1995.   DOI   ScienceOn
2 A. S. Malik and T. S. Choi, "Consideration of illumination effects and optimization of window size for accurate calculation of depth map for 3D shape recovery," Pattern Recognition, vol. 40, pp. 154 -170,2007.   DOI   ScienceOn
3 E. Krotkov, "Focusing," International Journal of Computer Vision, vol. 1, pp. 223 - 237, 1988.   DOI   ScienceOn
4 M. T. Mahmood, W. J. Choi, and T. S. Choi, "PCAbased method for 3D shape recovery of microscopic objects from image focus using discrete cosine transform," Microscopy Research and Technique, vol. 71, pp. 897 - 907, 2008.   DOI   ScienceOn
5 C. E. Rasmussen and C. K. I. Williams, Guussian Processes for Machine Learning: MIT Press, 2006.
6 Z. Jianke, S. C. H. Hoi, and M. R. Lyu, "Nonrigid shape recovery by Gaussian process regression," in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 2009, pp. 1319-1326.
7 N. Heung-Sun, W. Tai-Pang, and T. Chi-Keung, "Surface-from-Gradients with Incomplete Data for Single View Modeling," in Computer Vision, 2007.ICCV 2007. IEEE 11th International Conference on, 2007, pp. 1-8.
8 T. M. Tenenbaum, "Accommodation in computer vision," Stanford University, 1970.
9 R. Ferzli and L. J. Karam, "A No-Reference Objective Image Sharpness Metric Based on the Notion of Just Noticeable Blur (JNB)," Image Processing, IEEE Transactions on, vol. 18, pp. 717- 728, 2009.
10 T. S. Choi and J. Yun, "Three-dimensional shape recovery from the focused-image surface," Optical Engineering, vol. 39, pp. 1321 - 1326, 2000.   DOI   ScienceOn
11 M. B. Ahmad and T. S. Choi, "A heuristic approach for finding best focused shape," IEEE Transactions on Circuits and Systems for Video Technology, vol. 15, pp. 566 - 574, April 2005.   DOI
12 C. Hermans, Y. Francken, T. Cuypers, and P. Bekaert, "Depth from sliding projections," in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 2009, pp. 1865-1872.
13 A. P. Pentland, "A New Sense for Depth of Field," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. PAMI-9, pp. 523-531, 1987.   DOI
14 P. Favaro, S. Soatto, M. Burger, and S. J. Osher, "Shape from Defocus via Diffusion," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 30, pp. 518-531, 2008.   DOI
15 S. K. Nayar and Y. Nakagawa, "Shape from focus," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 16, pp. 824-831, Aug 1994.   DOI   ScienceOn