We proposed a novel 2D to 3D images conversion algorithm which automatically converts a single 2D image into the 3D effect images.
Compared our proposed algorithm with CID algorithm, we can find that our proposed algorithm has these advantages:
(1) This algorithm which combines image segmentation with depth extraction, so we can see the objects more complete on the 3D display.
(2) In the part of image segmentation, we proposed an image segmentation method which contains SSR (Single Scale Retinex) and the size filter. This image segmentation method is suitable for the 3D effect images.
(3) We proposed a novel method of depth extraction which could inference the object is horizontal or vertical, so we can feel more real stereo effect than CID algorithm on the 3D display.
(4) In order to reconstruct the left and right eye images from the depth map, we simulate the binocular vision to get the left and right eye images from the depth image.
Thus, we feel more comfortable about the 3D effect images on 3D display than CID algorithm.
In the future work, we could apply our algorithm on the 3D effect video. We can separate our algorithm into two parts. One part is image segmentation and the other is the part after image segmentation. We can combine some video segmentation methods with the part after image segmentation of our algorithm. Thus, we can generate the 3D effect video.
We think that we can add more depth cues to depth extraction. Thus, we can get more correct 3D effect images.
REFERENCES
[1] H. Murata, Y. Mori, S. Yamashita, A. Maenaka, S. Okada, K. Pyamada, and S.
Kishimoto, "A real- Time Image Conversion Technique Using Computed Image Depth," SID SYM, Vol. 29, pp. 919-922.
[2] T. Okino, H. Murata, K. Taima, T. Iinuma, and K. Oketani, "New television with 2D to 3D image conversion technologies," Proc. SPIE Stereoscopic Displays and Virtual Reality Systems III, Vol. 2653, pp. 96-103, 1996.
[3] T. S. Jebara, and A. Pentland, "Parametrized structure from motion for 3D adaptive feedback tracking of faces," Proceedings IEEE International Conference on Computer Vision and Pattern Recognition, pp. 144-150, 1997.
[4] E. Steinbach, A. Hanhalic, and B. Girod, "3D Motion and Scene Structure Estimation with Motion Dependent Distortion of Measurement Windows," Proceedings IEEE International Conference on Computer Vision, Vol. 1, pp. 434-422, 1999.
[5] C. T. Lin, and W. C. Cheng, "A Novel Post-Nonlinear ICA-Based Reflectance Model for 3D Surface Reconstruction," IEEE International Symposium on Circuits and Systems, May, 2005.
[6] A. Torralba and A. Oliva, "Depth Estimation from Image Structure,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 9 September 2002.
[7] S. Curti, D. Sirtori, and F. Vella "3D Effect Generation from Monocular View," IEEE Proceedings of the First International Symposium on 3D Data Processing Visualization and Transmission (3 DPVT`02), 2002.
[8] H. D. Cheng, X. H. Jiang, Y. Sun, and J. L. Wang, "Color image segmentation:
Advances and prospects", Pattern Recognition, 34(12), 2001.
[9] I. P, Howard, J. R. Brian, and A. P. Howard, Binocular Vision and Stereopsis, Oxford University Press, Chapter 7, 1995.
[10] R. Klette, K. Schluns, and A. Koschan, Computer Vision, Springer, pp. 29 - 33, 1998.
[11] E. Trucco, and A. Verri , Introductory Techniques for 3D Computer Vision, Prentice Hall, pp. 140-143, 1998.
[12] R. Z. Liu, "The design of stereo image on 2D monitor", The Master Thesis, 2001.
[13] N. Pal and S. Pal, "A review on image segmentation techniques," Pattern Recognition., vol. 26, no. 9, pp. 1277-1294, 1993.
[14] C. T. Lin, Y. C. Lee, and H. C. Pu, "Satellite sensor image classification using cascaded architecture of neural fuzzy network,” IEEE Transactions on Geoscience and Remote Sensing, Vol. 38, No. 2, pp.1033-1043, March 2000.
[15] C. T. Lin, W. C. Cheng, and S. F. Liang, "An on-line ICA-mixture-model-based self-constructing fuzzy neural network,” IEEE Transactions on Circuits and Systems I, vol. 52, no. 1, pp. 207-221, 2005.
[16] V. Mezaris, I. Kompatsiaris, and M. G.. Strintzis, "Still image segmentation tools for object-based multimedia applications," International Journal of Pattern Recognition and Arificial Intelligence, Vol. 18, No. 4, PP. 701-725, June 2004.
[17] E. Littmann and H. Ritter, "Adaptive color segmentation—a comparison of neural and statistical methods, " IEEE Trans. Neural Networks, vol. 8, Jan. 1997.
[18] T. Uchiyama and M. A. Arbib, "Color image segmentation using competitive learning,"
IEEE Trans. Pattern Anal. Machine Intelligence, vol. 16, pp. 1197-1206, Dec. 1994.
[19] H. D. Cheng, and Y. Sun, "A hierarchical approach to color image segmentation using homogeneity", IEEE Trans. on Image Processing, Vol. 9, No. 12, Dec 2000, p2071-2082.
[20] D. J. Jobson, Z. Rahman, and G.. A. Woodell, "Properties and performance of a center/surround retinex," IEEE Trans. Image Processing, vol. 6, pp. 451-462, Mar.
1997.
[21] D. C. Tseng and C. H. Chang, "Color segmentation using perceptual attributes, " in Proc. of 11th International Conf. on Pattern Recognition, vol.C, pp.228-231, 1992.
[22] J. Tajima, "Uniform color scale applications to computer graphics," Computer Vision, Graphics, and Image Processing, vol.21, pp.305-325, 1983.
[23] D. C. Tseng, Y. F. Li , and C. T. Tung, "Circular histogram thresholding for color image segmentation", Proceedings of the Third International Conference on Document Analysis and Recognition, Vol. 2, p. 673, August 14-155, 1995.
[24] N. Li and Y. F. Li, "Feature encoding for unsupervised segmentation of color images, "
IEEE Trans. On System Man and Cybernetics- Part B: Cybernetics, Vol. 33, No. 3, June 2003
[25] C. T. Lin and G.. Lee, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, Prentice Hall, 1996.
[26] D. Marr and T. Poggio, "Cooperative computation of stereo disparity," Science, 194:283-287, 1976.
[27] S. Barnard and M. Fischler, "Computational stereo," Computing Surveys, 14(4):553-572, December 1982.
[28] A. Pentland, "A new sense for depth of field," IEEE Trans. on Pattern Analysis and Machine Intelligence, 9(4):523-531, July 1981.
[29] G.. Surya and M. Subbarao, "Depth from defocus by changing camera aperture: a spatial domain approach," Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 61-6, 1993.
[30] N. Gershon, "Visualizing 3D PET images," IEEE Computer Graphics and Applications,
11(3):11-13, 1991.
[31] S. Marapane and M. Trivedi, "An active vision system for depth extraction using multi-primitive hierarchical stereo analysis and multiple depth cues," SPIE, 1956:250-262, 1993.
[32] R. Surdick, E. Davis, R. King and G.. Corso, "Relevant cues for the visual perception of depth: is where you see it where it is?" Proc. 38th mtg. Human Factors and Ergonomics Society, pp. 1305-1309, 1994.
[33] R. Srinivasan, M. Shridhar, and M. Ahmadi, "Computing surface information from monocular and binocular cues for vision applications," Proc. 27th Conf. Decision and Control, pp. 1085-1089, 1988.
[34] S. Das and N. Ahuja, "Dynamic integration of visual cues for position estimation,"
SPIE, 1382:341-352, 1990.