The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Three-dimensional Distortion-tolerant Object Recognition using Computational Integral Imaging and Statistical Pattern Analysis

집적 영상의 복원과 통계적 패턴분석을 이용한 왜곡에 강인한 3차원 물체 인식

  • 염석원 (대구대학교 정보통신공학부) ;
  • 이동수 (대구대학교 정보통신공학부) ;
  • 손정영 (대구대학교 정보통신공학부) ;
  • 김신환 (대구대학교 정보통신공학부)
  • Published : 2009.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we discuss distortion-tolerant pattern recognition using computational integral imaging reconstruction. Three-dimensional object information is captured by the integral imaging pick-up process. The captured information is numerically reconstructed at arbitrary depth-levels by averaging the corresponding pixels. We apply Fisher linear discriminant analysis combined with principal component analysis to computationally reconstructed images for the distortion-tolerant recognition. Fisher linear discriminant analysis maximizes the discrimination capability between classes and principal component analysis reduces the dimensionality with the minimum mean squared errors between the original and the restored images. The presented methods provide the promising results for the classification of out-of-plane rotated objects.

본 논문에서는 집적 영상의 획득과 복원을 이용하여 왜곡에 강인한 물체를 인식하는 방법을 연구한다. 해당 화소들의 확률적 특성인 평균과 표준편차를 이용하여 3차원 공간에서 물체를 복원하고 거리를 추정한다. 표적인식은 Fisher 선형판별법(linear discriminant analysis, LDA)과 주성분 분석법(principal component analysis, PCA) 기술을 결합한 통계적 분류기(statistical classifier)로 수행한다. Fisher 선형판별법은 클래스 간의 판별력을 최대로 하고 주성분 분석법은 Fisher 선형판별법을 수행하기 위한 차원축소를 실행한다. 주성분 분석법은 차원축소 후 복원된 벡터와 원 벡터의 오차를 최소화하는 기술로 알려져 있다. 실험 및 시뮬레이션을 통하여 면외(out-of-plane) 회전된 표적을 본 논문에서 제안한 방법으로 분류한다.

Keywords

References

  1. G. Lippmann, 'La photographie integrale,' C.R Acad. Sci., 146, pp. 446-451, 1908
  2. F. Okano, H. Hoshino, J. Arai, I. Yuyama, 'Real-time pickup method for a three-dimensional image based on integral photography,' Applied Optics, 36(7), pp. 1598-1603, March, 1997 https://doi.org/10.1364/AO.36.001598
  3. J. Son, V. V. Saveljev, Y. Choi, J. Bahn, S.-K Kim, H. Choi, 'Parameters for designing autostereoscopic imaging systems based on lenticular, parallax barrier, and integral photography plates,' Optics Engineering, 42(11), pp.3326-3333, November, 2003 https://doi.org/10.1117/1.1615259
  4. J. Jang, B. Javidi, 'Time-multiplexed integral imaging for 3D sensing and display,' Optics and Photonics News, 15(4), pp. 36-43, April, 2004
  5. S. Hong, J. Jang, B. Javidi, 'Three-dimensional volumetric object reconstruction using computational integral imaging,' Optics Express, 12(3), pp. 483-491, February 2004 https://doi.org/10.1364/OPEX.12.000483
  6. Y. Hwang, S. Hong, and B. Javidi, 'Free view 3-D visualization of occluded objects by using computational synthetic aperture integral imaging,' Journal of Display Technology, 3(1), pp.64-70, March 2007 https://doi.org/10.1109/JDT.2006.890702
  7. D. Hwang, D. Shin, S. Kim, E. Kim, 'Depth extraction of three-dimensional objects in space by the computational integral imaging reconstruction technique,' Applied Optics, 47(19), pp.D128-D135, July 2008 https://doi.org/10.1364/AO.47.00D128
  8. O. Matoba, E. Tajahuerce, B. Javidi, 'Real-time three-dimensional object recognition with multiple perspectives imaging,' Applied Optics, 40(20),pp. 3318-3325, July 2001 https://doi.org/10.1364/AO.40.003318
  9. J. Park, J. Kim, B. Lee, 'Three-dimensional optical correlator using a sub-image array,' Optics Express, 13(13), pp. 5116-5126, June 2005 https://doi.org/10.1364/OPEX.13.005116
  10. S. Yeom, B. Javidi, 'Three-dimensional distortion-tolerant object recognition using integral imaging,' Optics Express, 12(23), pp.5795-5809, November 2004 https://doi.org/10.1364/OPEX.12.005795
  11. S. Yeom, B. Javidi, and E. Watson, 'Photon counting passive 3D image sensing for automatic target recognition,' Optics Express, 13(23), pp. 9310-9330, November 2005 https://doi.org/10.1364/OPEX.13.009310
  12. S. Yeom, B. Javidi, C. Lee, E. Watson, 'Photon-counting passive 3D image sensing for reconstruction and recognition of partially occluded objects,' Optics Express, 15(24), pp.16189-16195, November 2007 https://doi.org/10.1364/OE.15.016189
  13. 이동수, 염석원, 김신환, 손정영, '집적 영상을 이용한 가려진 표적의 복원과 인식', 한국광학회지,19(4), pp. 270-275, August 2008 https://doi.org/10.3807/HKH.2008.19.4.270
  14. R. O. Duda, P. E. Hart, D. G. Stork, Pattern classification 2nd, Wiley Interscience, New York, pp. 114-124, 2001
  15. P. N. Belhumer, J. P. Hespanha, D. J. Kriegman, 'Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,' IEEE Trans. on PAMI., 19(7), pp. 711-720, July 1997 https://doi.org/10.1109/34.598228