A novel hybrid approach based on a chaotic cloud gravitational search algorithm to complicated image template matching

Template matching is the process of accurately extracting the interesting regions in a source image according to reference templates. In this paper, the gravitational search algorithm (GSA) is employed as a novel search strategy for template matching. However, the basic GSA is easily trapped in a local optimum and has a poor exploitation ability. In this paper, to enhance the optimization performance of GSA, a novel cross-search strategy based on chaotic global search (CGS) and cloud local search (CLS) is incorporated into GSA. The new variant is named chaotic cloud GSA (CCGSA). CGS makes full use of the ergodicity of chaos theory to improve global search ability and to avoid premature convergence. Inspired by the randomness and stable tendency of the normal cloud model, CLS was formed to realize a re ned exploitation in the neighborhood of the current best solution; therefore, it can enhance optimization efficiency. Comparative experiments on six composite benchmark functions indicate that CCGSA convergence performance is superior to that of two advanced variants of GSA. Moreover, when applied to template matching, CCGSA performs better than the other selected intelligent optimization algorithms.

PDF

___

[1] Belan PA, Araujo SA, Librantz AFH. Segmentation-free approaches of computer vision for automatic calibration of digital and analog instruments. Measurement 2013; 46: 177-184.
[2] Liu RM, Lu YH, Gong CL, Liu Y. Infrared point target detection with improved template matching. Infrared Phys Techn 2012; 55: 380-387.
[3] Di Caterina G, Soraghan JJ. Robust complete occlusion handling in adaptive template matching target tracking. Electron Lett 2012; 48: 831-U48.
[4] Zhu SP, Li Z, Yu Y. Virtual view synthesis using stereo vision based on the sum of absolute difference. Comput Electr Eng 2014; 40: 236-246.
[5] Tachibana H, Uchida Y, Shiizuka H. Technical note: Determination of the optimized image processing and template matching techniques for a patient intrafraction motion monitoring system. Med Phys 2012; 39: 755-764.
[6] Yoo JC, Ahn CW. Template matching of occluded object under low PSNR. Digit Signal Process 2013; 23: 870-878.
[7] Debella-Gilo M, Kaab A. Sub-pixel precision image matching for measuring surface displacements on mass move- ments using normalized cross-correlation. Remote Sens Environ 2011; 115: 130-142.
[8] Cheng L, Li MC, Liu YX, Cai WT, Chen YM, Yang K. Remote sensing image matching by integrating affine invariant feature extraction and RANSAC. Comput Electr Eng 2012; 38: 1023-1032.
[9] Senoussi H, Saoudi A. A quadtree algorithm for template matching on a pyramid computer. Theor Comput Sci 1994; 136: 387-417.
[10] Schubert A, Faes A, Kaab A, Meier E. Glacier surface velocity estimation using repeat TerraSAR-X images: Wavelet- vs. correlation-based image matching. ISPRS J Photogramm 2013; 82: 49-62.
[11] Liu F, Duan HB, Deng YM. A chaotic quantum-behaved particle swarm optimization based on lateral inhibition for image matching. Optik 2012; 123: 1955-1960.
[12] Gan L, Duan HB. Biological image processing via Chaotic Differential Search and lateral inhibition. Optik 2014; 125: 2070-2075.
[13] Zhang QF, Duan HB. Chaotic biogeography-based optimization approach to target detection in UAV surveillance. Optik 2014; 125: 7100-7105.
[14] Rashedi E, Nezamabadi-pour H, Saryazdi S. GSA: A gravitational search algorithm. Inform Sciences 2009; 179: 2232-2248.
[15] Altinoz OT, Yilmaz AE, Weber GW. Improvement of the gravitational search algorithm by means of low-discrepancy sobol quasi random-number sequence based initialization. Adv Electr Comput En 2014; 14: 55-62.
[16] Xiang J, Han XH, Duan F, Qiang Y, Xiong XY, Lan Y, Chai HS. A novel hybrid system for feature selection based on an improved gravitational search algorithm and k-NN method. Appl Soft Comput 2015; 31: 293-307.
[17] Ju FY, Hong WC. Application of seasonal SVR with chaotic gravitational search algorithm in electricity forecasting. Appl Math Model 2013; 37: 9643-9651.
[18] Yuan XF, Liu YM, Xiang YZ, Yan XG. Parameter identi cation of BIPT system using chaotic-enhanced fruit y optimization algorithm. Appl Math Comput 2015; 268: 1267-1281.
[19] Gandomi AH, Yang XS. Chaotic bat algorithm. J Comput Sci 2014; 5: 224-232.
[20] Zhao DS, He YZ. Chaotic binary bat algorithm for analog test point selection. Analog Integr Circ S 2015; 84: 201-214.
[21] Li DY, Meng HJ, Shi XM. Membership clouds and membership cloud generators. J Comput Res Dev 1995; 32: 15-20 (in Chinese with an abstract in English).
[22] Wang GY, Xu CL, Li DY. Generic normal cloud model. Inform Sciences 2014; 280: 1-15.
[23] Liang JJ, Suganthan PN, Deb K. Novel composition test functions for numerical global optimization. In: IEEE Swarm Intelligence Symposium; 8{10 June 2005; Pasadena, CA, USA: IEEE. pp. 68-75.
[24] Mirjalili S, Gandomi AH. Chaotic gravitational search constants for the gravitational search algorithm. Appl Soft Comput 2017; 53: 407-419.
[25] Guvenc U, Katrcoglu F. Escape velocity: a new operator for gravitational search algorithm. Neural Comput Appl 2017; 1-16. DOI: 10.1007/s00521-017-2977-9.