Application of Texture Features and Machine Learning Methods to Grain Segmentation in Rock Material Images
DOI:
https://doi.org/10.5566/ias.2186Keywords:
classification, grain sizes, object segmentation, texture featuresAbstract
The segmentation of rock grains on images depicting bulk rock materials is considered. The rocks’ material images are transformed by selected texture operators, to obtain a set of features describing them. The first order features, second-order features, run-length matrix, grey tone difference matrix, and Laws’ energies are used for this purpose. The features are classified using k-nearest neighbours, support vector machines, and artificial neural networks classifiers. The results show that the border of rocks grains can be determined with above 75% accuracy. The multi-texture approach was also investigated, leading to an increase in accuracy to over 79% for the early-fusion of features. Attempts were made to reduce feature space dimensionality by manually picking features as well as by the use of principal component analysis. The outcomes showed a significant decrease in accuracy. The obtained results have been visually compared with the ground truth. The compliance observed can be considered to be satisfactory.
References
Ailleres L, Champenois M, Macaudiere J, Bertrand J (1995). Use of image analysis in the measurement of finite strain by the normalized Fry Method: geological implications for the ‘Zone Houillère’ (Briançonnais zone, French Alps). Mineral Mag 59:179--87.
Al-Thyabat S, Miles N (2006). An improved estimation of size distribution from particle profile measurements. Powder Technol 166:152 -- 160.
Aldrich C, Jemwa G, Van~Dyk J, Keyser M, Van~Heerden J (2010). Online analysis of coal on a conveyor belt by use of machine vision and kernel methods. Int J Coal Prep Util 30:331--48.
Alpana, Mohapatra S (2015). Automated coal characterization using computational intelligence and image analysis techniques. In: 2015 Communication, Control and Intelligent Systems (CCIS).
Alpana, Mohapatra S (2016). Machine learning approach for automated coal characterization using scanned electron microscopic images. Comput Ind 75:35 -- 45.
Amadasun M, King R (1989). Textural features corresponding to textural properties. IEEE T Syst Man Cyb 19:1264--74.
Burges CJC (1998). A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121--67.
Chang CC, Lin CJ (2011). Libsvm: A library for support vector machines. ACM T Intel Syst Tec 2:27:1--27:27.
Chatterjee S, Bhattacherjee A (2011). Genetic algorithms for feature selection of image analysis-based quality monitoring model: An application to an iron mine. Eng Appl Artif Intel 24:786 -- 795.
Cord A, Bach F, Jeulin D (2010). Texture Classification By Statistical Learning From Morphological Image Processing: Application To Metallic Surfaces. J Microsc Oxford 239:159--66.
Galloway MM (1975).
Texture analysis using gray level run lengths.
Comput Vision Graph 4:172 -- 179.
Gurney K (1997).
An Introduction to Neural Networks.
Bristol, PA, USA: Taylor & Francis, Inc.
Guyot O, Monredon T, LaRosa D, Broussaud A (2004).
Visiorock, an integrated vision technology for advanced control of
comminution circuits.
Miner Eng 17:1227 -- 1235.
Communition '04.
Haines TJ, Neilson JE, Healy D, Michie EA, Aplin AC (2015).
The impact of carbonate texture on the quantification of total porosity by image analysis.
Comput Geosci 85:112 -- 125.
Haralick RM, Shanmugam K, Dinstein I (1973).
Textural features for image classification.
IEEE T Syst Man Cyb SMC-3:610--21.
Hulthén E, Evertsson CM (2009).
Algorithm for dynamic cone crusher control.
Miner Eng 22:296 -- 303.
Igathinathane C, Ulusoy U (2016).
Machine vision methods based particle size distribution of ball- and gyro-milled lignite and hard coal.
Powder Technol 297:71 -- 80.
Igathinathane C, Ulusoy U, Pordesimo L (2012).
Comparison of particle size distribution of celestite mineral by machine vision volume approach and mechanical sieving.
Powder Technol 215-216:137 -- 146.
Kemeny J, Mofya E, Kaunda R, Lever P (2002).
Improvements in blast fragmentation models using digital image processing.
Fragblast 6:311--20.
Kistner M, Jemwa GT, Aldrich C (2013).
Monitoring of mineral processing systems by using textural image analysis.
Miner Eng 52:169--77.
Ko YD, Shang H (2011).
A neural network-based soft sensor for particle size distribution using image analysis.
Powder Technol 212:359 -- 366.
Kwan A, Mora C, Chan H (1999).
Particle shape analysis of coarse aggregate using digital image processing.
Cement Concrete Res 29:1403 -- 1410.
Latała Z, Wojnar L (2001).
Computer-aided versus manual grain size assessment in a single phase material.
Mater Charact 46:227 -- 233.
STERMAT 2000: Stereology and Image Analysis in Materials Science.
Laws KI (1980).
Rapid texture identification.
In: Proc.SPIE, vol. 0238.
Lobos R, Silva JF, Ortiz JM, Díaz G, Egaña A (2016).
Analysis and Classification of Natural Rock Textures based on New Transform-based Features.
Math Geosci 48:835--70.
Lu B, Cui M, liu Q, Wang Y (2009).
Automated grain boundary detection using the level set method.
Comput Geosci 35:267 -- 275.
Lumbreras F, Serrat J (1996).
Segmentation of petrographical images of marbles.
Comput Geosci 22:547 -- 558.
Maerz N (1998).
Aggregate sizing and shape determination using digital image processing.
In: Center For Aggregates Research (ICAR) Sixth Annual
Symposium Proceedings.
Materka A, Strzelecki M (1998).
Texture analysis methods -- a review.
Tech. rep., Institute of Electronics, Technical University of Lodz.
Mertens G, Elsen J (2006).
Use of computer assisted image analysis for the determination of the grain-size distribution of sands used in mortars.
Cement Concrete Res 36:1453 -- 1459.
th EUROSEMINAR on microscopy applied to building materials, University of Paisley, June 21-25, 2005.
Mlynarczuk M, Ladniak M, Piorkowski A (2014).
Application of database technology to analysis of rock structure images.
PHYSICOCHEM PROBL MI Vol. 50, iss. 2:563--73.
Mora C, Kwan A, Chan H (1998).
Particle size distribution analysis of coarse aggregate using digital image processing.
Cement Concrete Res 28:921 -- 932.
Murphy KP (2013).
Machine learning : a probabilistic perspective.
Cambridge, Mass. [u.a.]: MIT Press.
Murtagh F, Qiao X, Crookes D, Walsh P, Basheer PAM, Long A, Starck JL (2005).
A machine vision approach to the grading of crushed aggregate.
Mach Vision Appl 16:229--35.
Obuchowicz R, Nurzynska K, Obuchowicz B, Urbanik A, Piórkowski A (2018).
Caries detection enhancement using texture feature maps of intraoral radiographs.
Oral Radiol .
Ojala T, Pietikainen M, Maenpaa T (2002).
Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.
IEEE T Pattern Anal 24:971--87.
Outal S (2006).
Quantification by image analysis of the size distribution of fragmented rocks: improvment of the morphological extraction of surfaces, improvment of the stereological rebuilding.
These, Ecole Nationale Superieure des Mines de Paris.
Outal S, Beucher S (2009).
Controlling the ultimate opening residues for a robust delineation of fragmetned rocks.
In: The 10th European Congress of Stereology and Image Analysis,
Milan, Italy. ~6.
Outal S, Jeulin D, Schleifer J (2008).
A new method for estimating the 3D size-distributioncurve of fragmented rocks out of 2D images.
Image Analysis Stereology 27:97--105.
Outal S, Schleifer J, Pirard E (2009).
Evaluating a calibration method for the estimation of fragmented rock 3d-size-distribution out of 2d images.
In: FRAGBLAST 9—Proc. 9th International Symposium on Rock
Fragmentation by Blasting, Granada, 13--17 September.
Perez CA, Estévez PA, Vera PA, Castillo LE, Aravena CM, Schulz DA, Medina LE
(2011).
Ore grade estimation by feature selection and voting using boundary detection in digital image analysis.
Int J Miner Process 101:28 -- 36.
Piorkowski A (2017).
Best-fit segmentation created using flood-based iterative thinning.
In: Choras R, ed., Image Processing and Communications Challenges 8.
IP&C 2016, vol. 525 of AISC. Springer, 61--8.
Siddiqui F, Shah SMA, Behan MY (2010).
Measurement of size distribution of blasted rock using digital image processing.
Tang X (1998).
Texture information in run-length matrices.
IEEE T Image Process 7:1602--9.
Tessier J, Duchesne C, Bartolacci G (2007).
A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor belts.
Miner Eng 20:1129 -- 1144.
Thurley MJ (2013).
Automated image segmentation and analysis of rock piles in an open-pit mine.
In: Digital Image Computing: Techniques and Applications (DICTA),
International Conference on. IEEE.
Wang W (1999).
Image analysis of aggregates.
Comput Geosci 25:71 -- 81.
Wang W (2006).
Image analysis of particles by modified ferret method — best-fit rectangle.
Powder Technol 165:1 -- 10.
Wang W (2008).
Rock particle image segmentation and systems.
In: Pattern Recognition Techniques, Technology and Applications.
InTech.
Yaghoobi H, Mansouri H, Farsangi MAE, Nezamabadi-Pour H (2019).
Determining the fragmented rock size distribution using textural feature extraction of images.
Powder Technol 342:630--41.
Zhang Z, JianguoYang, Su X, Ding L, Wang Y (2013).
Multi-scale image segmentation of coal piles on a belt based on the hessian matrix.
Particuology 11:549 -- 555.
Downloads
Published
Issue
Section
License
Copyright (c) 2020 Image Analysis & Stereology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
