Multi-view Image Registration Method Based on Fuzzy Matching
DONG Tian-Zhen1,2, DENG Ting-Quan1, DAI Jia-Shu1, XIE Wei1,3 , MA Ming-Hua1
1.Laboratory of Fuzzy Information Analysis and Intelligent Recognition, Harbin Engineering University, Harbin 150001 2.School of Computer Science and Information Engineering, Shanghai Institute of Technology, Shanghai 201148 3.School of Applied Sciences, Harbin University of Science and Technology, Harbin 150080
Abstract According to the characteristics of spatial multi-view images, a fuzzy matching based multi-view image registration method is proposed by the principle of coarse-to-fine. Based on image segmentation, the uncertainty of the information from multi-view images is taken into account. The robust regional features such as area, dominant hue and second order moments of brightness are regarded as descriptors of connected regions and then the connected regions are fuzzed. By introducing fuzzy implication, the matching degree between connected regions in multi-view images is calculated. Then, the best matching relation between connected regions is built via fuzzy reasoning. Finally, the feedback correction is used for matching relationship between feature points of connected regions. The adaptive accurate registration between multi-view images is achieved. Meanwhile, the validity of the proposed method is demonstrated through experiments.
[1] Goshtasby A A. 2-D and 3-D Image Registration: For Medical, Remote Sensing, and Industrial Applications[EB/OL]. [2013-01-12]. http://onlinelibrary.wiley.com/book/10.1002/0471724270 [2] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110 [3] Mortensen E N, Deng H L, Shapiro L. A SIFT Descriptor with Global Context // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, I: 184-190 [4] Wu P C, Wang Z Y, Lin X T. Color Image Registration Algorithm Using Local Derivative Pattern Approach. Journal of Xi'an Jiaotong University, 2011, 45(10): 30-37 (in Chinese) (吴攀超,王宗义,林欣堂.采用局部差分模型描述的彩色图像配准技术.西安交通大学学报, 2011, 45(10): 30-37) [5] Bouchafa S, Zavidovique B. Efficient Cumulative Matching for Ima- ge Registration. Image and Vision Computing, 2006, 24(1): 70-79 [6] Adewuyi T D O. Stress and On-line Registration among Fresh Students in Lagos State University. Procedia Computer Science, 2011, 3: 654-658 [7] Bunting P, Labrosse F, Lucas R. A Multi-resolution Area-Based Technique for Automatic Multi-modal Image Registration. Image and Vision Computing, 2010, 28(8): 1203-1219 [8] Ming A L, Ma H D.Region-SIFT Descriptor Based Correspondence between Multiple Cameras. Chinese Journal of Computers, 2008, 31(4): 650-661 (in Chinese) (明安龙,马华东.多摄像机之间基于区域SIFT描述子的目标匹配.计算机学报, 2008, 31(4): 650-661) [9] Zheng Z G, Wang Z F. A Region Based Stereo Matching Algorithm Using Cooperative Optimization. Acta Automatica Sinica, 2009, 35(5): 469-477 (in Chinese) (郑志刚,汪增福.基于区域间协同优化的立体匹配算法.自动化学报, 2009, 35(5): 469-477) [10] Wang J Q, Shi Z L, Huang S B. An Improved Image Matching Algorithm Based on Moment Invariant. Pattern Recognition and Artificial Intelligence, 2005, 18(2): 228-233 (in Chinese) (王俊卿,史泽林,黄莎白.一种改进的基于不变矩的图像匹配算法.模式识别与人工智能, 2005, 18(2): 228-233) [11] You F, Feng Y B, Li H X. Fuzzy Implication Operators and Their Construction-Fuzzy Implication Operators and Their Properties. Journal of Beijing Normal University: Natural Science, 2003, 39(5): 606-611 (in Chinese) (尤 飞,冯艳宾,李洪兴.模糊蕴涵算子及其构造(Ⅰ)——模糊蕴涵算子及其性质.北京师范大学学报:自然科学版, 2003,39(5): 606-611)"|||887"[1] Wang B B, Guo J W, Xie J D, et al. Application of Fuzzy Petri Net Knowledge Representation in Fault Diagnosis Expert System of Transformers. Proceedings of the EPSA, 2003, 15(1): 74-77 (in Chinese) (王蓓蓓,郭基伟,谢敬东,等.基于模糊Petri网的知识表示方法在变压器故障诊断专家系统中的应用.电力系统及其自动化学报, 2003, 15(1): 74-77) [2] Wei S J, Hu C Z, Sun M Q. A Method of Dynamic Knowledge Re- presentation and Reasoning Based on Fuzzy Petri Nets. Science and Technology Review, 2007, 25(7): 13-17 (in Chinese) (危胜军,胡昌振,孙明谦.基于模糊Petri网的动态知识表示与推理方法.科技导报, 2007, 25(7): 13-17) [3] Li Y, Yue X B. Application of Ant Colony Algorithm in Parameters Optimization of Fuzzy Petri Nets. Journal of Compute Applications, 2007, 27(3): 638-641(in Chinese) (李 洋,乐晓波.蚁群算法在模糊 Petri 网参数优化中的应用.计算机应用, 2007, 27(3): 638-641) [4] Li X, Lara-Rosano F. Adaptive Fuzzy Petri Nets for Dynamic Knowledge Representation and Inference. Expert Systems with Applications, 2000, 19(3): 235-241 [5] Bao P M. Learning Capability in Fuzzy Petri Nets Based on BP Net. Chinese Journal of Computers, 2004, 27(5): 695-702 (in Chinese) (鲍培明.基于BP网络的模糊Petri网的学习能力.计算机学报, 2004, 27(5): 695-702) [6] Xu H, Jia P F. Fuzzy Timed Object-Oriented Petri Net // Proc of the 2nd IFIP Conference on Artificial Intelligence Applications and Innovations. Beijing, China, 2005: 155-166 [7] Peters J F, Pawlak Z, Skowron A. A Rough Set Approach to Mea- suring Information Granules // Proc of the 26th Annual International Computer Software and Applications Conference. Oxford, UK, 2002: 1135-1139 [8] Wang W M, Hu J, Yin J L, et al. A Knowledge-Based Parameter Consistency Management System for Concurrent and Collaborative Design. Journal of Engineering Manufacture. 2007, 221 (1): 97-107
2014, Vol. 27 
