Abstract Stereo correspondence matching is a key problem in many applications like computer and robotic vision to determine Three%Dimensional (3D) depth information of objects which is essential for 3D reconstruction. This paper presents a 3D reconstruction technique with a fast stereo co rrespondence matching which is robust in tackling a dditive noise. The additive noise is eliminated using a fuzzy filterin g technique. Experimentations with ground truth ima ges prove the effectiveness of the proposed algorithms.

References

[1] Barnard S., Stereo Matching by Hierarchical, Microcanonical Annealing, in Proceedings of the International Joint Conference on Artificial Intelligence , Italy, pp. 832 835, 1987.

[2] Barnard S. and Fishler M., Stereo Vision, in Proceedings of Encyclopedia of Artificial Intelligence , New York, pp. 1083 1090, 1987.

[3] Calin G. and Roda V., Real Time Disparity Map Extraction: A Dual Head Stereo Vision System, Latin American Applied Research , vol. 37, no. 1, pp. 21 24 2007.

[4] Chowdhury M., Mondal A., and Bhuiyan M., 3D Imaging using Stereo Vision, in Proceedings of the 7 th International Conference on Computer and Information Technology , pp. 307 312, 2004.

[5] Chowdhury M. and Bhuiyan M., A New Approach for Disparity Map Determination, Daffodil International University Journal of Science and Technolog y, vol. 4, no. 1, pp. 9 13, 2009.

[6] Fua P., A Parallel Stereo Algorithm that Produces Dense Depth Maps and Preserves Image Features, Machine Vision and Applications , vol. 6, no. 1, pp. 35 49, 1993.

[7] Fusiello A., Trucco E., and Roberto V., Efficient Stereo with Multiple Windowing, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , USA, pp. 858 863, 1997.

[8] Hannah M., A System for Digital Stereo Image Matching, Photogrammetric Engineering and Remote Sensing , vol. 55, no. 12, pp. 1765 1770, 1989.

[9] Hoff W. and Ahuja N., Surface From Stereo: Integrating Feature Matching, Disparity Estimation and Contour Detection, IEEE Transaction on Pattern Analysis and Machine Intelligence , vol. 11, no. 2, pp. 121 136, 1989.

[10] Hu T. and Huang M., A New Stereo Matching Algorithm for Binocular Vision, International Journal of Hybrid Information Technology , vol. 3, no. 1, pp. 1 8, 2010.

[11] Intille S. and Bobick A., Disparity Space Images and Large Occlusion Stereo, in Proceedings of the European Conference on Computer Vision , Sweden, pp. 179 186, 1994.

[12] Kanade T. and Okutomi M., A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment, IEEE Transaction on Pattern Analysis and Machine Intelligence , vol. 16, no. 9, pp. 920 932, 1994.

[13] Lmaati E., Oirrak A., Kaddioui M., Ouahman A., and Sadgal M., 3D Model Retrieval Based on 3D Discrete Cosine Transform, The International Arab Journal of Information Technology , vol. 7, no. 3, pp. 264 270, 2010.

[14] Matondang M. and Haron H., Hybrid Computing Algorithm in Representing Solid Model, The International Arab Journal of Information Technology , vol. 7, no. 4, pp. 411 419, 2010.

[15] Muhlmann K., Maier D., Hesser J., and Manner R., Calculating Dense Disparity Maps from Color Stereo Images an Efficient Implementation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , Kauai, pp. 30 36, 2001 .

[16] Uddin M., Chowdhury M., Shioyama T., and Mondal M., Fast Window Based Approach for Stereo Matching, Journal of Science, vol. 27, pp. 145 154, 2004.

[17] Veksler O., Stereo Matching by Compact Windows Via Minimum Ratio Cycle, in Proceedings of the IEEE International Conference on Computer Vision , Vancouver, pp. 540 547, 2001. Mohammad Mozammel Chowdhury is working as an Associate Professor in the Department of Computer Science and Engineering, Jahangirnagar University, Savar, Dhaka, Bangladesh. He received his BSc degree in Electronics and Computer Science and MS degree in Computer Science and Engineering from the same university. H e has published more than 25 articles in reputed jour nals and conference proceedings. His research interest includes: image processing, computer vision, roboti cs, 3d scene reconstruction, computer graphics and machine intelligence. Mohammad AL-Amin Bhuiyan is a Professor in the Department of Computer Science and Engineering, Jahangirnagar University, Savar, Dhaka, Bangladesh. He got the PhD degree in Electrical engineering from Osaka City University, Japan, he did the post doctoral research from National Institute of Informatics, Japan and University of Hull, UK. His research interest includes: robotics, image process ing, computer vision, face recognition, human robot symbiosis.