Abstract
This paper proposes a novel image segmentation method based on BP neural network, which is optimized by an enhanced Gravitational Search Algorithm (GSA). GSA is a novel heuristic optimization algorithm based on the law of gravity and mass interactions. It has been proven that the GSA has good ability to search for the global optimum, but it suffers from the premature convergence due to the rapid reduction of diversity. This work introduces a cat chaotic mapping into the steps of population initialization and iterative stage of the original GSA, which forms a new algorithm called CCMGSA. Then the CCMGSA is employed to optimize BP neural networks, which forms a combination method called CCMGSA-BP and we use it for image segmentation. To verify the efficiency of this method, the visual and performance experiments are done. The visual results using our proposed method are compared with those using other segmentation methods including an improved k-means clustering algorithm (I-K-means), a hybrid region merging method (H-Region-merging), and manual segmentation. The comparison results show that the proposed method can get good segmentation results on grayscale images with specific characteristics. And we compare the performance of our proposed method with those of IGSA-BP, CLPSO-BP and RGA-BP for image segmentation. The results indicate that the CCMGSA-BP shows better performance in terms of the convergence rate and avoidance of local minima.
Similar content being viewed by others
References
Algeelani NA, Piah M, Afendi M, Zuraimy A, Munir A (2013) Hybrid regrouping PSO based wavelet neural networks for characterization of acoustic signals due to surface discharges on H.V. glass insulators. Appl Soft Comput 13 :4622–4632
Chakraborti T, Sharma KD, Chatterjee A (2014) A novel local extrema based gravitational search algorithm and its application in face recognition using one training image per class. Eng Appl Artif Intell 34:13–22
Chang CL, Ching YT (2002). Opt Eng 41:351–358
Dash M, Choi K, Scheuermann P, Liu H (2002) Feature selection for clustering—a filter solution. Proceedings of the Second IEEE International Conference on Data Mining (ICDM’02), IEEE Computer Society Washington, DC, USA
Dekruger D, Hunt BR (1994). Pattern Recog-nition 27:461–483
Gao C, Zhou DG, Guo YC (2013) Automatic iterative algorithm for image segmentation using a modified pulse-coupled neural network. Neurocomputing 119:332–338
Goktepe M, Yaiabik N, Atalay VU (1996) Supervised segmentation of gray level Markov model textures with hierarchical self organizing map. Proceedings of the13th International Conference on Pattern Recognition. USA: Institute of Electricand Electronic Engineer, 90-94
Gonzalez Rafael C, Richard E (2002) Woods:digital image processing.2nd ed. Prentice Hall, India
Hatamlou A, Abdullah S, Nezamabadi-Pour H (2011) Application of gravitational search algorithm on data clustering, rough sets and knowledge technology. Sci 6954:337–346
Hatamlou A, Abdullah S, Nezamabadi-Pour H (2012) A combined approach for clustering based on K-means and gravitational search algorithms. Swarm Evol Comput 6:47–52
Holland JH (1975) Adaptation in nature and artificial systems. University of Michigan Press, Ann Arbor
Ikonomakis N, Plataniotis KN, Zervakis M, Venetsanopoulos AN (1997) Region growing and region merging image segmentation. International Conference on Digital Signal Processing DSP 1:299–301
Ismail A, Jeng DS, Zhang LL (2013) An optimised product-unit neural network with a novel PSO–BP hybrid training algorithm: Applications to load–deformation analysis of axially loaded piles. Eng Appl Artif Intell 26:2305–2314
Iscan Z, Yüksel A, Dokur Z, Korürek M, Olmez T (2009) Medical image segmentation with transform and moment based features and incremental supervised neural network. Digital Signal Processing: A Review Journal 19:890–901
Ito N, Kamekura R, Shimazu Y, Yokoyama T, Matsushita Y (1996) Combination of edge detection and region extraction in nonparametric color image segmentation. Inf Sci 92:277–294
Jain PK, Susan S (2013) An adaptive single seed based region growing algorithm for color image segmentation. 2013 Annual IEEE India Conference, INDICON
John C (1986) A Computational Approach to Edge Detection. IEEE Trans Pattern Anal Mach Intell 8:679–698
Ju ZW, Zhou JL, Wang X, Shu Q (2013) Image segmentation based on adaptive threshold edge detection and mean shift. Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS
Kennedy J, Eberhart RC (1995) Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, vol 4, pp 1942–1948
Kim J-Y, Kim L-S, Hwang S-H An advanced contrast enhancement using partially overlapped sub-block histogram equalization. IEEE Trans Circuits Syst Video Technol 11:475–484
Kumar V, Chhabra JK, Kumar D (2014) Automatic cluster evolution using gravitational search algorithm and its application on image segmentation. Eng Appl Artif Intell 29:93–103
Kuntimad G, Ranganath HS (1999) Perfect image segmentation using pulse coupled neural networks. IEEE Trans Neural Netw 10(3):591–598
Li MW, Hong WC, Kang HG (2013) Urban traffic flow forecasting using Gauss–SVR with cat mapping, cloud model and PSO hybrid algorithm. Neurocomputing 99:230–240
Li JB, Liu XG (2011) Melt index prediction by RBF neural network optimized with an MPSO-SA hybrid algorithm. Neurocomputing 74:735–740
Lin CH, Chen CC (2010) Image segmentation based on edge detection and region growing for thinprep-cervical smear. Int J Pattern Recognit Artif Intell 24:1061–1089
Liu K, Guo WY, Shen XL, Tan ZF (2012) Research on the Forecast Model of Electricity Power Industry Loan Based on GA-BP Neural Network. Energy Procedia 14:1918–1924
Mahadevan K, Kannan P S (2010) Comprehensive learning particle swarm optimization for reactive power dispatch. Appl Soft Comput 10:641–652
Martin D, Fowlkes C (2001) A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. In Proceedings Proc. 8th Int’l Conf. Comput Vis 2:416–423
Melo-Pinto P, Couto P, Bustince H, Barrenechea E, Pagola M, Fernandez J (2013) Image segmentation using Atanassov’s intuitionistic fuzzy sets. Expert Systems with Applications 40:15–26
Mitra P, Murthy CA, Pal SK (2002) Unsupervised feature selection using feature similarity. IEEE Trans Pattern Anal Mach Intell 24:301–312
Musharavati F, Hamouda A S M (2011) Modified genetic algorithms for manufacturing process planning in multiple parts manufacturing lines. Expert Systems with Applications 38:10770–10779
Nabizadeh N, John N, Wright C (2014) Histogram-based gravitational optimization algorithm on single MR modality for automatic brain lesion detection and segmentation. Expert Systems with Applications 41:7820–7836
Nambiar VP, Khalil-Hani M, Marsono MN, Sia CW (2014) Optimization of structure and system latency in evolvable block-based neural networks using genetic algorithm. Neurocomputing 145:285–302
Pancerz K, Lewicki A (2014) Encoding symbolic features in simple decision systems over ontological graphs for PSO and neural network based classifiers. Neurocomputing 144 :338–345
Pujar JH, Gurjal PS, Shambhavi DS, Kunnur KS (2010) Medical image segmentation based on vigorous smoothing and edge detection ideology. World Acad Sci Eng Technol 68 :444–450
Raya TH, Bettaiah V, Ranganath HS (2011) Adaptive Pulse Coupled Neural Network parameters for image segmentation. World Acad Sci Eng Technol 73:1046–1052
Rout S, Srivastava S, Majumdar J (1998) Multi-modal image seg-mentation using a modified Hopfield neural network. Pat-tern Recognition 31:743–750
Rashedi E, Nezamabadi H, Saryazdi S (2009) GSA: a gravitational search algorithm. Inform Sci 179:2232–2248
Rashedi E, Nezamabadi H, Saryazdi S (2010) BGSA: binary gravitational search algorithm. Nat Comput 9:727–745
Sarafrazi S, Nezamabadi-pour H, Saryazdi S (2011) Disruption: A new operator in gravitational search algorithm. Scientia Iranica 18:539–548
Sergi R, Satalino G, Solaiman B, Pasquariello G (1996) SIR-C polarimetric image segmentation by neural network. International Geoscience and Remote Sensing Symposium (IGARSS) 3:1562–1564
Shih FY, Cheng SX (2005) Automatic seeded region growing for color image segmentation. Image Vis Comput 23 :877–886
Simon K (2009) Neural networks and learning machines, 3rd ed. Pearson Education, New Jersey
Sun G, Zhang A (2013) A hybrid genetic algorithm and gravitational search algorithm for image segmentation using multil evel thresholding. Pattern Recognit. Image Anal. Lect. Notes Comput Sci 7887:707–714
Vilarino DL, Brea VM, Cabello D (1998) Discrete Time CNN for Image segmentation by active contours. Pattern Recogn Lett 19:721–734
Wang YL, Lin KC, Yu HM, Li QJ, Li ZX, Wang XW (2011) A new ISODATA image segmentation algorithm based on intuitionistic fuzzy. Adv Mater Res 187:309–312
Wang XY, Wang T, Bu J (2011) Color image segmentation using pixel wise support vector machine classification. Pattern Recogn 44:777–787
Wang DL, Terman D (1997) Image segmentation based on oscillatory correlation. Neural Comput 9:805–836
Wang Y, Adaii T, Kung SY (1998) Quantification and segmentation of brain tissues from MR images a probabilistic neural net-works approach. IEEE Trans Image Process 7(8):1–12
Weng GR, Zhang BS, Cheng DJ (2008) Leukocytes color image segmentation and extraction based on mathematical morphology. Int J Inf Comput Sci 5:521–528
Xiao WC, Chen WH (2013) A sensing image segmentation scheme based on support vector machine and LBP model. International Journal of Applied Mathematics and Statistics 51:484–493
Hong Y, Qingling D, Li D, Jianping W (2013) An improved k-means clustering algorithm for fish image segmentation. Math Comput Model 58:790–798
Yin X, Guo D, Xie M (2001) Hand image segmentation using color and RCE neural network. Robot Auton Syst 34 :235–250
Yu F, Xu XZ (2014) A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network. Appl Energy 134:102–113
Zhang Y, Zhou SF, Lin ZZ (2013) Cotton and bast fiber image segmentation based on mathematical morphology. Applied Mechanics and Materials 303-306:1590–1594
Zhang Y, Yu B, Gu HM (2012) Multi-level document image segmentation using multi-layer perceptron and support vector machine. International Journal of Pattern Recognition and Artificial Intelligence, 26
Zhang JR, Zhang J, Lock TM, Lyu MR (2007) A hybrid particle swarm optimization–back-propagation algorithm for feed forward neural network training. Appl Math Comput 128:1026–1037
Xueliang Z, Pengfeng X, Xuezhi F, Jiangeng W, Zuo W (2014) Hybrid region merging method for segmentation of high-resolution remote sensing images. ISPRS J Photogramm Remote Sens 98:19–28
Zhuo L, Zhang J, Dong P, Zhao YD, Peng B (2014) An SA–GA–BP neural network-based color correction algorithm for TCM tongue images. Neurocomputing 134:111–116
Acknowledgments
This research has been supported by Natural Science Foundation of Shanxi Province of China (2014011021-1) and National Natural Science Foundation program of China (61202163 and 61373100).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Han, X., Xiong, X. & Duan, F. A new method for image segmentation based on BP neural network and gravitational search algorithm enhanced by cat chaotic mapping. Appl Intell 43, 855–873 (2015). https://doi.org/10.1007/s10489-015-0679-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-015-0679-5