An evaluation of global thresholding techniques for the automatic image segmentation of automotive aluminum sheet alloys

wbldb

Lievers, W. B.¹; Pilkey, A. K.²

An evaluation of global thresholding techniques for the automatic image segmentation of automotive aluminum sheet alloys

Mater Sci Eng. September 15, 2004;A381(1-2):134-142

©2004 Elsevier B.V. All rights reserved.

Affiliations

¹Centre for Automotive Materials and Manufacturing, 945 Princess Street, Kingston, Ont., Canada K7L 5L9

²Department of Mechanical and Materials Engineering, Queen’s University, Kingston, Ont., Canada K7L 3N6
Abstract and keywords

Digital image analysis is a valuable tool for the quantification of microstructural morphology, such as the size and clustering distributions of second-phase particles. However, the first step to such analysis is the segmentation of digital micrographs to identify the features of interest. Since the outcome of this step will have a significant influence on all subsequent processing, accurate segmentation is of the utmost importance. Grayscale images of the microstructures of three automotive aluminum alloys are used (AA5182, AA5754, and AA6111) to compare the abilities of several automatic global image thresholding techniques. The minimum cross-entropy method of Li and Lee [Pattern Recognit. 30 (1993) 617] was found to work well for all alloys when combined with the cost function of Yen et al. [IEEE T. Image Process. 4 (1995) 370].

Keywords: Automotive aluminum; Threshold; Segmentation; Image analysis
Links

DOI: 10.1016/j.msea.2004.04.002

WoS: 000223738500018
History

Received: 2003-12-15

Revised: 2004-04-1

Online: 2004-06-7

Cited Works (30)

Year	Entry
1985	Tsai W-H. Moment-preserving thresolding: a new approach. Comput Vis Graph Image Proc. 1985;29(3):377-393.
1999	Li M, Ghosh S, Richmond O. An experimental–computational approach to the investigation of damage evolution in discontinuously reinforced aluminum matrix composite. Acta Mater. 1999;47(12):3515-3532.
2001	Conlon KT, Wilkinson DS. Effect of particle distribution on deformation and damage of two-phase alloys. Mater Sci Eng. 2001;A317(1-2):108-114.
1995	Yen J-C, Chang F-J, Chang S. A new criterion for automatic multilevel thresholding. IEEE Trans Image Process. March 1995;4(3):370-378.
1986	Kittler J, Illingworth J. Minimum error thresholding. Patt Recogn. 1986;19(1):41-47.
1993	Li CH, Lee CK. Minimum cross entropy thresholding. Patt Recogn. 1993;26(4):617-625.
1989	Wong AKC, Sahoo PK. A gray-level threshold selection method based on maximum entropy principle. IEEE Trans Sys Man Cyb. 1989;19(4):866-871.
1988	Sahoo PK, Soltani S, Wong AKC. A survey of thresholding techniques. Comput Vis Graph Image Proc. 1988;41(2):233-260.
1985	Haralick RM, Shapiro LG. Image segmentation techniques. Comput Vis Graph Image Proc. January 1985;29(1):100-132.
1989	Abutaleb AS. Automatic thresholding of gray-level pictures using two-dimensional entropy. Comput Vis Graph Image Proc. 1989;47(1):22-32.
1993	Glasbey CA. An analysis of histogram-based thresholding algorithms. CVGIP: Graph Models Im Proc. November 1993;55(6):532-537.
1998	Pilkey AK, Worswick MJ, Thomson CIE, Burger G, Lloyd DJ. Effect of second-phase particle clustering on formability of Al-Si sheet. In: Wilkinson DS, Poole W, Alpas A, eds. Advances in Industrial Materials. The Metallurgical Society of CIM; 1998:105-121.
1990	Lee SU, Chung SY, Park RH. A comparative performance study of several global thresholding techniques for segmentation. Comput Vis Graph Image Proc. November 1990;52(2):171-190.
1989	Pal N, Pal S. Entropic thresholding. Signal Process. 1989;16(2):97-108.
2001	Yang X, Beyenal H, Harkin G, Lewandowski Z. Evaluation of biofilm image thresholding methods. Water Res. April 2001;35(5):1149-1158.
2003	Thomson CIA, Worswick MJ, Pilkey AK, Lloyd DJ. Void coalescence within periodic clusters of particles. J Mech Phys Solids. 2003;51(1):127-146.
1996	Zhang YJ. A survey on evaluation methods for image segmentation. Patt Recogn. 1996;29(8):1335-1346.
1978	Weszka JS. A survey of threshold selection techniques. Comput Graph Image Proc. 1978;7(2):259-265.
1966	Prewitt JMS, Mendelsohn ML. The analysis of cell images. Annals NY Acad Sci. January 1966;128(3):1035-1053.
2001	Worswick MJ, Chen ZT, Pilkey AK, Lloyd D, Court S. Damage characterization and damage percolation modelling in aluminum alloy sheet. Acta Mater. August 16, 2001;49(14):2791-2803.
1999	Thomson CIA, Worswick MJ, Pilkey AK, Lloyd DJ, Burger G. Modeling void nucleation and growth within periodic clusters of particles. J Mech Phys Solids. 1999;47(1):1-26.
1979	Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Sys Man Cyb. 1979;9(1):62-66.
2002	Baveye P. Comment on "evaluation of biofilm image thresholding methods". Water Res. 2002;36(3):805-806.
1985	Kapur JN, Sahoo PK, Wong AKC. A new method for gray-level picture thresholding using the entropy of the histogram. Comput Vis Graph Image Proc. 1985;29(3):273-285.
1997	Sahoo P, Wilkins C, Yeager J. Threshold selection using Renyi's entropy. Patt Recogn. January 1997;30(1):71-84.
1978	Ridler TW, Calvard S. Picture thresholding using an iterative selection method. IEEE Trans Sys Man Cyb. 1978;8(8):630-632.
1981	Fu KS, Mui JK. A survey on image segmentation. Patt Recogn. 1981;13(1):3-16.
1994	O'Gorman L. Binarization and multithresholding of document images using connectivity. CVGIP: Graph Models Im Proc. November 1994;56(6):494-506.
2000	Seul M, O'Gorman L, Sammon MJ. Practical Algorithms for Image Analysis: Description, Examples, and Code. Cambridge, UK: Cambridge University Press; 2000.
1993	Pal N, Pal S. A review on image segmentation techniques. Patt Recogn. 1993;23(9):1277-1294.

Cited By (28)

Year	Entry
2011	Balaji TK, Krishnaveni K, Kenny SPK. A fuzzy optimal threshold technique for medical images. In: Zeng Z, Li Y, eds. Proceedings of the 4th International Conference on Machine Vision (imcv 2011): Machine Vision, Image Processing, and Pattern Analysis. December 9-10, 2011; Singapore. Proceedings of the SPIE; vol 8349.
2009	Chen L, Guo L, Yang N, Du Y. Multi-level image thresholding based on histogram voting. Proceedings of the 2009 2nd International Congress on Image and Signal Processing (CISP '09); September 17-19, 2009; Tianjin, China.1841-1845.
2013	Cho SH, Duy HT, Han JW, Hwang H. Multi-level thresholding based on non-parametric approaches for fast segmentation. J Biosystems Eng. 2013;38(2):149-162.
2010	Hammouche K, Diaf M, Siarry P. A comparative study of various meta-heuristic techniques applied to the multilevel thresholding problem. Eng Appl Artificial Intell. 2010;23(5):676-688.
2016	Hussein WA, Sahran S, Abdullah SNHS. A fast scheme for multilevel thresholding based on a modified bees algorithm. Knowledge-Based Syst. June 1, 2016;101:114-134.
2005	Jonckheere I, Nackaerts K, Muys B, Coppin P. Assessment of automatic gap fraction estimation of forests from digital hemispherical photography. Agr Forest Meteorol. 2005;132(1-2):96-114.
2012	Kumar SS, Balakrishnan G, Swetha EA. Fuzzy optimal threshold for cervical images. Int J Commun Eng. March 2012;1(4):34-40.
2014	Mahapatra PK, Kaur M, Sethi S, Thareja R, Kumar A, Devi S. Improved thresholding based on negative selection algorithm (NSA). Evol Intel. February 2014;6(3):157-170.
2011	Pradnyana GA, Suputra IPGH. HYBRID GENETIC ALGORITHM DAN ANT COLONY OPTIMIZATION UNTUK OPTIMISASI METODE MULTILEVEL IMAGE THRESHOLDING. J Ilmiah Teknol Info. July 2011;9(2):28-36.
2009	Wei D, Zhao Y. Estimation of crystal size distribution based on photomicrograph. Proceedings of the 21st annual international conference on Chinese Control and Decision Conference; 2009; Guilin, China.1465-1470.
2007	Xie G, Zhang Q, Louzguine DV, Zhang W, Inoue A. Stability of nanocrystallites dispersed in Cu50Zr45Ti5 metallic glass under electron irradiation. J Nanosci Nanotech. 2007;7(9):3286-3293.
2009	Xinying X, Zhijun Z, Jun X, Keming X. Threshold image segmentation based on granular immune algorithm. Proceedings of the 21st annual international conference on Chinese Control and Decision Conference; 2009; Guilin, China.3512-3515.
2006	Zhang Y-j. A summary of recent progresses for segmentation evaluation. In: Zhang Y-j, ed. Advances in Image and Video Segmentation. London: IRM Press; 2006:423-440.
2004	Lievers WB, Pilkey AK, Lloyd DJ. Using incremental forming to calibrate a void nucleation model for automotive aluminum sheet alloys. Acta Mater. June 7, 2004;52(10):3001-3007.
2015	DeCost BL, Holm EA. A computer vision approach for automated analysis and classification of microstructural image data. Comp Mater Sci. December 2015;110:126-133.
2016	Chowdhury A, Kautz E, Yener B, Lewis D. Image driven machine learning methods for microstructure recognition. Comp Mater Sci. October 2016;123:176-187.
2008	Hammouche K, Diaf M, Siarry P. A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation. Comput Vis Image Und. 2008;109(2):163-175.
2010	De Albuquerque VHC, Filho PPR, Cavalcante TS, Tavares JMRS. New computational solution to quantify synthetic material porosity from optical microscopic images. J Microsc (Oxford). 2010;240(1):50-59.
2020	Gupta S, Banerjee A, Sarkar J, Kundu M, Sinha SK, Bandyopadhyay NR, Ganguly S. Modelling the steel microstructure knowledge for in-silico recognition of phases using machine learning. Mater Chem Phys. September 15, 2020;252:123286.
2021	Jaques VAJ, Du Plessis A, Zemek M, Šalplachta J, Stubianová Z, Zikmund T, Kaiser J. Review of porosity uncertainty estimation methods in computed tomography dataset. Meas Sci Technol. December 2021;32(12):122001.
2020	Gupta S, Sarkar J, Kundu M, Bandyopadhyay NR, Ganguly S. Automatic recognition of SEM microstructure and phases of steel using LBP and random decision forest operator. Measurement. February 2020;151:107224.
2009	Lievers WB, Pilkey AK. Matrix-erosion tessellation: comparing particle clustering measures extracted from three-dimensional vs two-dimensional images. Metall Mater Trans. 2009;A40(1):36-45.
2011	De Albuquerque VHC, Silva CC, Menezes TIdS, Farias JP, Tavares JMRS. Automatic evaluation of nickel alloy secondary phases from SEM images. Microsc Res Tech. 2011;74(1):36-46.
2022	Lei B. Data-Driven Image Segmentation of Complex Microstructures With Deep Learning [PhD thesis]. Carnegie Mellon University; December 2022.
2022	Luengo J, Moreno R, Sevillano I, Charte D, Peláez-Vegas A, Fernández-Moreno M, Mesejo P, Herrera F. A tutorial on the segmentation of metallographic images: taxonomy, new MetalDAM dataset, deep learning-based ensemble model, experimental analysis and challenges. Inf Fusion. February 1, 2022;78:232.
2022	Fredriksson D. Machine Learning Methods for Segmentation of Complex Metal Microstructure Features [Master's thesis]. Sweden, Royal Institute of Technology; 2022.
2018	Scott H. Effects of Microstructure and Particle Population on Void Damage Evolution in Complex Phase Steel [PhD thesis]. Queen's University; September 2018.
2008	Na X. Nonlinear Identification and Control: A Practical Solution and Its Application [PhD thesis]. Lexington, KY: University of Kentucky; 2008.