3D-modeling of deformed halite hopper crystals by Object Based Image Analysis

Object Based Image Analysis (OBIA) is an established method for analyzing multiscale and multidimensional imagery in a range of disciplines. In the present study this method was used for the 3D reconstruction of halite hopper crystals in a mudrock sample, based on Computed Tomography data. To quantitatively assess the reliability of OBIA results, they were benchmarked against a corresponding "gold standard", a reference 3D model of the halite crystals that was derived by manual expert digitization of the CT images. For accuracy assessment, classical per-scene statistics were extended to per-object statistics. The strength of OBIA was to recognize all objects similar to halite hopper crystals and in particular to eliminate cracks. Using a support vector machine (SVM) classifier on top of OBIA, unsuitable objects like halite crystal clusters, polyhalite-coated crystals and spherical halite crystals were effectively dismissed, but simultaneously the number of well-shaped halites was reduced. Object Based Image Analysis was used for 3D reconstruction of halite hopper crystals.A support vector machine classifier on top of OBIA dismissed unsuitable objects.The result was benchmarked against a corresponding "gold standard".For accuracy assessment, per-scene statistics were extended to per-object statistics.

[1]  Anna Rotarska-Jagiela,et al.  The corpus callosum in schizophrenia-volume and connectivity changes affect specific regions , 2008, NeuroImage.

[2]  Shigeo Abe.  Support Vector Machines for Pattern Classification , 2010, Advances in Pattern Recognition.

[3]  A. Kendall,et al.  Compaction in halite‐cemented carbonates – the Dawson Bay Formation (Middle Devonian) of Saskatchewan, Canada , 2000 .

[4]  G. Meinel,et al.  EVALUATION OF SEGMENTATION PROGRAMS FOR HIGH RESOLUTION REMOTE SENSING APPLICATIONS , 2003 .

[5]  Norman Kerle,et al.  3D object-oriented image analysis in 3D geophysical modelling: Analysing the central part of the East African Rift System , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[6]  Dirk Tiede,et al.  ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data , 2010, Int. J. Geogr. Inf. Sci..

[7]  P. Jacobs,et al.  Applications of X-ray computed tomography in the geosciences , 2003, Geological Society, London, Special Publications.

[8]  Thomas Blaschke,et al.  Geographic Information Science as a Common Cause for Interdisciplinary Research , 2012, AGILE Conf..

[9]  Peter Hofmann,et al.  Solid modeling of fossil small mammal teeth , 2011, Comput. Geosci..

[10]  Maria Athelogou,et al.  Cognition Network Technology – A Novel Multimodal Image Analysis Technique for Automatic Identification and Quantification of Biological Image Contents , 2007 .

[11]  Susanne Nelskamp,et al.  Dynamics of Complex Intracontinental Basins : The Central European Basin System , 2008 .

[12]  Peter Hofmann,et al.  Marble provenance designation with Object Based Image Analysis: State-of-the-art rock fabric characterization , 2013 .

[13]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[14]  Dirk Gajewski,et al.  Dynamics of Complex Intracontinental Basins , 2008 .

[15]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[16]  Thomas Blaschke,et al.  Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[17]  Dirk Tiede,et al.  Supervised and forest type-specific multi-scale segmentation for a one-level-representation of single trees , 2006 .

[18]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

[19]  R. Görgey,et al.  Zur Kenntnis der Kalisalzlager von Wittelsheim im Ober-Elsaß , 1912 .

[20]  I. Dan Melamed,et al.  Precision and Recall of Machine Translation , 2003, NAACL.

[21]  János Urai,et al.  Flow and transport properties of salt rocks , 2005 .

[22]  B. Charlotte Schreiber,et al.  Displacive Halite Hoppers from the Dead Sea: Some Implications for Ancient Evaporite Deposits , 1981 .

[23]  F. Neubauer,et al.  Origin of deformed halite hopper crystals, pseudomorphic anhydrite cubes and polyhalite in Alpine evaporites (Austria, Germany) , 2012, International Journal of Earth Sciences.

[24]  Xueliang Zhang,et al.  Support vector machine-based decision tree for snow cover extraction in mountain areas using high spatial resolution remote sensing image , 2014 .

[25]  Thomas Blaschke,et al.  Geographic Object-Based Image Analysis – Towards a new paradigm , 2014, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[26]  Anna Rotarska-Jagiela,et al.  Automated segmentation of lateral ventricles from human and primate magnetic resonance images using cognition network technology. , 2006, Magnetic resonance imaging.

[27]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[28]  Peter A. Calabresi,et al.  OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI☆ , 2013, NeuroImage: Clinical.

[29]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[30]  R. Ketcham,et al.  Acquisition, optimization and interpretation of X-ray computed tomographic imagery: applications to the geosciences , 2001 .

[31]  S. Timmermanns,et al.  The Challenge of Evidence-Based Medicine and Standardization in Health Care , 2003 .

[32]  Stuart J. Russell,et al.  Artificial Intelligence , 1986 .

[33]  Kathleen C. Benison,et al.  Sedimentology of Ancient Saline Pans: An Example from the Permian Opeche Shale, Williston Basin, North Dakota, U.S.A. , 2000 .

[34]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[35]  Christian Igel,et al.  Evolutionary tuning of multiple SVM parameters , 2005, ESANN.

[36]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[37]  Russell Congalton,et al.  Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Second Edition , 1998 .

[38]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[39]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[40]  Alexander Heidrich,et al.  Automated Segmentation and Object Classification of CT Images: Application to In Vivo Molecular Imaging of Avian Embryos , 2013, Int. J. Biomed. Imaging.

[41]  A. Tzotsos,et al.  Support Vector Machine Classification for Object-Based Image Analysis , 2008 .

[42]  Friedrich Frischknecht,et al.  Imaging Cellular and Molecular Biological Functions , 2007 .

[43]  W. Haidinger.  Ueber die Pseudomorphosen nach Steinsalz , 1847 .