2-D minimum error threshold segmentation method based on mean absolute deviation from the median

SONG Bin; YANG Huixian; ZENG Jinfang; TAN Zhenghua; LI Cuiju

doi:10.7510/jgjs.issn.1001-3806.2015.05.028

In order to solve the problem that 2-D minimum error threshold segmentation (METS) method had poor segment robust performance on an image which presents skew distribution and heavy-tailed distribution, an improved 2-D METS method was proposed based on mean absolute deviation from the median. Considering that the median was a more robust estimator of gray level than the mean in 1-D histogram of skew distribution and heavy-tailed distribution, variance in 2-D METS was replaced by mean absolute deviation from the median. In order to improve the computational speed, a 2-D algorithm was decomposed into two 1-D algorithms. Experimental results show that, compared with 2-D Otsu method, 2-D METS method and other classical algorithms, the improved 2-D METS method based on mean absolute deviation has more accurate segmentation results and more robust performance for 1-D histogram with skew distribution and heavy-tailed distribution.

2-D minimum error threshold segmentation method based on mean absolute deviation from the median

Corresponding author: YANG Huixian, yanghx@xtu.edu.cn;

1. The School of Physics and Optoelectronics, Xiangtan University, Xiangtan 411105, China;

2. The School of Information Engineering, Xiangtan University, Xiangtan 411105, China

Received Date: 2014-07-30

Accepted Date: 2014-09-05

Available Online: 2015-09-25

Abstract: In order to solve the problem that 2-D minimum error threshold segmentation (METS) method had poor segment robust performance on an image which presents skew distribution and heavy-tailed distribution, an improved 2-D METS method was proposed based on mean absolute deviation from the median. Considering that the median was a more robust estimator of gray level than the mean in 1-D histogram of skew distribution and heavy-tailed distribution, variance in 2-D METS was replaced by mean absolute deviation from the median. In order to improve the computational speed, a 2-D algorithm was decomposed into two 1-D algorithms. Experimental results show that, compared with 2-D Otsu method, 2-D METS method and other classical algorithms, the improved 2-D METS method based on mean absolute deviation has more accurate segmentation results and more robust performance for 1-D histogram with skew distribution and heavy-tailed distribution.

HTML

Reference (15)

[1]	DIRAMI A, HAMMOUCHE K, DIAF M, et al.Fast multilevel thresholding for image segmentation through a multiphase level set method[J]. Signal Processing,2013,93(1):139-153.
[2]	MOGHADDAM R F, CHERIET M. AdOtsu:An adaptive and parameterless generalization of Otsu's method for document image binarization[J]. Pattern Recognition,2012,45(6):2419-2431.
[3]	SATHYA P D, KAYALVIZHI R. Amended bacterial foraging algorithm for multilevel thresholding of magnetic resonace brain images[J].Measurement,2011,44(10):1828-1848.
[4]	KITTLER J, ILLINGWORHT J. Minimum error thresholding [J]. Pattern Recognition, 1986,19(1):41-47.
[5]	GONG J, LI L Y, CHEN W N. Fast recursive algorithms for two-dimensional thresholding[J].Pattern Recognition,1998,31(3):295-300.
[6]	SEZGIN M, SANKUR B. Survey over image thresholding techniques and quantitative performance evaluation [J]. Journal of Electronic Imaging,2004,13(1):146-168.
[7]	FAN J L, LEI B. Two-dimensional extension of minimum error threshold segmentation method for gray-level images[J]. Acta Automatica Sinica,2009,35(4):386-393(in Chinese).
[8]	ZHU D Q, JING L Q, BI R S, et al. Improvement algorithm of minimum-error thresholding segmentation method[J]. Opto-Electronic Engineering,2010,37(7):107-113(in Chinese).
[9]	WU Y Q, ZHANG X J, WU Sh H, et al. Two-dimensional minimum error thresholding based on chaotic particle swarm optimization or decomposition[J]. Journal of Zhejiang University(Engineer Science Edition),2011,45(7):1198-1205(in Chinese).
[10]	ZHANG X M, FENG W H, HE W T, et al. Two-dimensional minimum error thresholding method nased on the artificial bee colony algorithm[J]. Journal of Guangxi University(Natural Science Edition),2013, 38(5):1126-1133(in Chinese).
[11]	XUE J H, TITTERINGTON D M. Median-based image thresholding[J]. Image and Vision Computing,2011,29(9):631-637.
[12]	LIU J, YU Z B, JIN W D. Three dimentional minimum error thres-hold algorithm and its fast recursive mathod[J].Journal of Electronics Information Technology,2013,35(9):2073-2080(in Chinese).
[13]	CUI T Y, LIU W P, ZHANG N. Algorithms and performance comparison of automatic thresholdingsegmentation for forest regions in remote sensing image[J]. Journal of Computer Applications,2010,30(12):3269-3273(in Chinese).
[14]	YUE F, ZUO W M, WANG K Q. Decomposition based two-dimensional thresholdalgorithm for grayimages[J]. Acta Automatica Sinica,2009,35(7): 1022-1027(in Chinese).
[15]	GONG Q, NI L, TANG P F, et al. Fast three-dimensional Otsu image segmentation algorithm based on decomposition[J]. Journal of Computer Applications,2012,32(6):1526-1528(in Chinese).

2-D minimum error threshold segmentation method based on mean absolute deviation from the median

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views