Characterizing powder materials using keypoint-based computer vision methods

Abstract We applied the bag of visual words model for visual texture to a dataset of realistic powder micrograph images drawn from eight closely related particle size distributions. We found that image texture based powder classification performance saturates at 89 ± 3 % with 640 training images (80 images per class). This classification accuracy is comparable to classification using conventional segmentation-based particle size analysis. Furthermore, we found that particle size distributions obtained via watershed segmentation are generally not statistically equivalent to the ground truth particle size distributions, as quantified by the two-sample Kolmogorov-Smirnov test for distribution equivalence. We expect image texture classification methods to outperform particle size analysis for more challenging real-world powder classification tasks by capturing additional information about particle morphology and surface textures, which add complexity to the image segmentation task inherent in particle size distribution estimation.

[1]  O. Lyckfeldt,et al.  Characterization and Control of Powder Properties for Additive Manufacturing , 2015 .

[2]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[3]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[4]  Elizabeth A. Holm,et al.  A large dataset of synthetic SEM images of powder materials and their ground truth 3D structures , 2016, Data in brief.

[5]  Andrew Zisserman,et al.  A Statistical Approach to Material Classification Using Image Patch Exemplars , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[8]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[9]  Brian Armstrong,et al.  The Application of Powder Rheology in Additive Manufacturing , 2015 .

[10]  Douglas Steinley,et al.  K-means clustering: a half-century synthesis. , 2006, The British journal of mathematical and statistical psychology.

[11]  Kevin W Eliceiri,et al.  NIH Image to ImageJ: 25 years of image analysis , 2012, Nature Methods.

[12]  Roland Siegwart,et al.  BRISK: Binary Robust invariant scalable keypoints , 2011, 2011 International Conference on Computer Vision.

[13]  S. Kalidindi,et al.  Novel microstructure quantification framework for databasing, visualization, and analysis of microstructure data , 2013, Integrating Materials and Manufacturing Innovation.

[14]  R. Poprawe,et al.  Laser additive manufacturing of metallic components: materials, processes and mechanisms , 2012 .

[15]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[16]  Roland Hess,et al.  The Essential Blender: Guide to 3D Creation with the Open Source Suite Blender , 2007 .

[17]  Claus Emmelmann,et al.  Investigation of Aging Processes of Ti-6Al-4 V Powder Material in Laser Melting , 2012 .

[18]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[19]  R. L. Thorndike.  Who belongs in the family? , 1953 .

[20]  M. Graef,et al.  Quantifying the abnormal strain state in ferroelastic materials: A moment invariant approach , 2015 .

[21]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[22]  Jerry Y. H. Fuh,et al.  The influence of powder apparent density on the density in direct laser-sintered metallic parts , 2007 .

[23]  Hongyi Xu,et al.  A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures , 2015 .

[24]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[25]  F. Massey.  The Kolmogorov-Smirnov Test for Goodness of Fit , 1951 .

[26]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[27]  Surya R. Kalidindi,et al.  Microstructure informatics using higher-order statistics and efficient data-mining protocols , 2011 .

[28]  Ma Qian,et al.  Effect of Powder Reuse Times on Additive Manufacturing of Ti-6Al-4V by Selective Electron Beam Melting , 2015 .

[29]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[30]  R. German.  Powder metallurgy and particulate materials processing : the processes, materials, products, properties and applications , 2005 .

[31]  J. Kruth,et al.  Powder deposition in selective metal powder sintering , 1995 .

[32]  Andrea Vedaldi,et al.  Vlfeat: an open and portable library of computer vision algorithms , 2010, ACM Multimedia.

[33]  Abdolreza Simchi,et al.  The role of particle size on the laser sintering of iron powder , 2004 .

[34]  Shawn P. Moylan,et al.  Measurement Science Needs for Real-time Control of Additive Manufacturing Powder Bed Fusion Processes , 2015 .

[35]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[36]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[37]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[38]  Vadas Gintautas,et al.  Particle Size Analysis by Laser Diffraction Spectrometry: Application to Cementitious Powders. , 2004 .

[39]  Cordelia Schmid,et al.  A sparse texture representation using local affine regions , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  M. Peltz,et al.  Characterization of Metal Powders Used for Additive Manufacturing , 2014, Journal of research of the National Institute of Standards and Technology.

[41]  Luc Vincent,et al.  Determining watersheds in digital pictures via flooding simulations , 1990, Other Conferences.

[42]  William E. Frazier,et al.  Metal Additive Manufacturing: A Review , 2014, Journal of Materials Engineering and Performance.

[43]  E. Garboczi,et al.  Metrology Needs for Metal Additive Manufacturing Powders , 2015 .

[44]  Elizabeth A. Holm,et al.  A computer vision approach for automated analysis and classification of microstructural image data , 2015 .

[45]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[46]  Florent Perronnin,et al.  Modeling the spatial layout of images beyond spatial pyramids , 2012, Pattern Recognit. Lett..

[47]  Frédéric Jurie,et al.  Sampling Strategies for Bag-of-Features Image Classification , 2006, ECCV.