3D Surface Reconstruction by Combining Focus Measures through Genetic Algorithm

유전 알고리즘 기반의 초점 측도 조합을 이용한 3차원 표면 재구성 기법

  • 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)
  • Received : 2014.05.27
  • Accepted : 2014.06.20
  • Published : 2014.06.30

Abstract

For the reconstruction of three-dimensional (3D) shape of microscopic objects through shape from focus (SFF) methods, usually a single focus measure operator is employed. However, it is difficult to compute accurate depth map using a single focus measure due to different textures, light conditions and arbitrary object surfaces. Moreover, real images with diverse types of illuminations and contrasts lead to the erroneous depth map estimation through a single focus measure. In order to get better focus measurements and depth map, we have combined focus measure operators by using genetic algorithm. The resultant focus measure is obtained by weighted sum of the output of various focus measure operators. Optimal weights are obtained using genetic algorithm. Finally, depth map is obtained from the refined focus volume. The performance of the developed method is then evaluated by using both the synthetic and real world image sequences. The experimental results show that the proposed method is more effective in computing accurate depth maps as compared to the existing SFF methods.

Keywords

References

  1. M. T. Mahmood and Y. K. Choi, "3D Shape Recovery from Image Focus using Gaussian Process Regression," Journal of the Semiconductor & Display Technonogy, vol. 11, no. 3, pp. 19-25, 2012.
  2. M. Subbarao and J. K. Tyan, "Selecting the optimal focus measure for autofocusing and depth-from-focus," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 864-870, 1998. https://doi.org/10.1109/34.709612
  3. S. Nayar and Y. Nakagawa, "Shape from Focus: An Effective Approach for Rough Surfaces," in International Conference on Robotics and Automation, vol. 1, pp. 218-225, May 1990.
  4. M. T. Mahmood, W. J. Choi and T. S. Choi, "PCA-based method for 3d shape recovery of microscopic objects from image focus using discrete cosine transform," Microscopy Research and Technique, vol. 71, no. 12, pp. 897-907, 2008. https://doi.org/10.1002/jemt.20635
  5. M. T. Mahmood, S. O. Shim and T. S. Choi, "Shape from focus using principal component analysis in discrete wavelet transform," Optical Engineering, vol. 48, 2009.
  6. S. K. Nayar and Y. Nakagawa, "Shape from focus," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, pp. 824-831, 1994 https://doi.org/10.1109/34.308479
  7. J. H. Holland, "Adaptation in natural and artificial systems," University of Michigan Press, pp. 59-84, 1975.
  8. T. Tenenbaum, "Accommodation in computer vision," Doctoral Dissertation, Stanford University, 1970.
  9. E. Krotkov, "Focusing," International Journal of Computer Vision, vol. 1, pp. 223 - 237, 1988. https://doi.org/10.1007/BF00127822
  10. C. K. Chow, H. T. Tsui and T. Lee, "Surface registration using a dynamic genetic algorithm," Pattern Recognition, vol. 37, no. 1, pp. 105-117, 2004. https://doi.org/10.1016/S0031-3203(03)00222-X
  11. M. Srinivas and L. M. Patnaik, "Genetic algorithms: A survey," Computer, pp. 17-26, 1994.