Fast Computation of Threshold Based on Multi-threshold Otsu Criterion
SHEN Xuanjing LIU Xiang CHEN Haipeng
(College of Computer Science and Technology, Jilin University, Changchun 130012, China)
(Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China)
To resolve the problem of low efficiency which traditional multi-threshold Otsu existing in searching of optimal thresholds on the brute-force method, the thresholds properties of multi-threshold Otsu are analyzed, and the mathematical correspondence is proved between a set of optimal thresholds and the means of various categories. A new algorithm is proposed to calculate the optimal thresholds and a new model of searching thresholds is also built according to the properties of thresholds of multi-threshold Otsu. The algorithm searches for a set of optimal thresholds that satisfy the correspondence between the thresholds and the means of various categories segmented by them, so the optimal thresholds of Otsu can be determined. The algorithm reduces the search range effectively and optimizes the calculation of means and variances using lookup table. Experimental results show that the segmentation speed of the algorithm is greatly improved compared with the traditional multi-threshold Otsu method, and the algorithm can not only improve the computation speed, but also overcome the shortcomings of randomness and contingency of thresholds compared with other fast multi-threshold Otsu algorithm, and the results are strictly in line with the principle of multi-threshold Otsu.
申铉京,刘翔,陈海鹏. 基于多阈值Otsu准则的阈值分割快速计算[J]. 电子与信息学报, 2017, 39(1): 144-149.
SHEN Xuanjing, LIU Xiang, CHEN Haipeng. Fast Computation of Threshold Based on Multi-threshold Otsu Criterion. JEIT, 2017, 39(1): 144-149.
SHEN Xuanjing, LONG Jianwu, CHEN Haipeng, et al. Otsu thresholding algorithm based on rebuilding and dimension reduction of the 3-dimensional histogram[J]. Acta Electronica Sinica, 2011, 39(5): 1108-1114.
WANG Haiyang, PAN Delu, and XIA Deshen. A fast algorithm for two-dimensional Otsu adaptive threshold algorithm[J]. Acta Automatica Sinica, 2007, 33(9): 968-971. doi: 10.16383/j.aas.2007.09.004.
[3]
OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on System, Man, and Cybemetics, 1979, 9(1): 62-66.
LIU Li, JIAO Binliang, and LIU Qinlong. Otsu multi- threshold promotion and realization of Otsu multi-threshold segmentation method[J]. Science of Surveying and Mapping, 2009, 34(6): 240-241.
LIU Yan and ZHAO Yingliang. Quick approach of multi-threshold Otsu method for image segmentation[J]. Journal of Computer Applications, 2011, 31(12): 3363-3365. doi: 10.3724/SP.J.1087.2011.03363.
[6]
HAMMOUCHE K, DIAF M, and SIARRY P. A comparative study of various meta-heuristic techniques applied to the multilevel thresholding problem[J]. Engineering Applications of Artificial Intelligence, 2010, 23(5): 676-688. doi: 10.1016 /j.engappai.2009.09.011.
[7]
HORNG Minghuwi. A multi-level image thresholding using the honey bee mating optimization[J]. Applied Mathematics and Computation, 2010, 215(9): 3302-3310. doi: 10.1016/ j.amc.2009.10.018.
ZHANG Huaizhu, XIANG Changbo, SONG Jianzhong, et al. Application of improved adaptive genetic algorithm to image segmentation in real-time[J]. Optics and Precision Engineering, 2008, 16(2): 333-338.
[9]
BHANDARI A K, KUMAR A, and SINGH G K. Modified artificial bee colony based computationally efficient multilevel thresholding for satellite image segmentation using Kapur’s, Otsu and Tsallis functions[J]. Expert Systems with Applications, 2015, 42(3): 1573-1601. doi: 10.1016/j.eswa. 2014.09.049.
[10]
CHEN Zezhi , PEARS N, FREEMAN M, et al. Background subtraction in video using recursive mixture models, spatio- temporal filtering and shadow removal[C]. International Symposium on Visual Computing, Berlin, Germany, 2009: 1141-1150. doi: 10.1007/978-3-642-10520-3_109.
[11]
ARORA S, ACHARYA J, VERMA A, et al. Multi-level thresholding for image segmentation through a fast statistical recursive algorithm[J]. Pattern Recognition Letters, 2008, 29(2): 119-125. doi: 10.1016/j.patrec.2007.09.005.
FAN Jiulun, ZHAO Feng, and ZHANG Xuefeng. Recursive algorithm for three-dimensional Otsu,s thresholding segmentation method[J]. Acta Electronica Sinica, 2007, 35(7): 1398-1402.
[13]
WU Peng. Image segmentation method based on firefly algorithm and maximum entropy method[J]. Computer Engineering and Applications, 2014, 50(12): 115-119.
QU Shiru and YANG Honghong. Infrared image segmentation based on PCNN with genetic algorithm parameter optimization[J]. High Power Laser and Particle Beams, 2015, 27(5): 38-43. doi: 10.11884/HPLPB201527. 051007.
[15]
YUAN Xiaocui, WU Lushen, and PENG Qingjin. An improved Otsu method using the weighted object variance for defect detection[J]. Applied Surface Science, 2015, 349(15): 472-484. doi: 10.1016/j.apsusc.2015.05.033.
[16]
FAYCAL?Hamdaoui, ANIS?Sakly, and ABDELLATIF Mtibaa. Computational Intelligence Applications in Modeling and Control[M]. Germany: Springer, 2015: 343-367.
HE Zhiyong, SUN Lining, and CHEN Liguo. Fast computation of threshold based on Otsu criterion[J]. Acta Electronica Sinica, 2013, 41(2): 267-272. doi: 10.3969/j. issn.0372-2112. 2013.02.010.
