Unsupervised feature learning for autonomous rock image classification

Abstract Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

[1]  Steve Chien,et al.  Automated Targeting for the MER Rovers , 2009, 2009 Third IEEE International Conference on Space Mission Challenges for Information Technology.

[2]  T. Estlin,et al.  Autonomous onboard traverse science system , 2004, 2004 IEEE Aerospace Conference Proceedings (IEEE Cat. No.04TH8720).

[3]  Mariusz Młynarczuk,et al.  Application of pattern recognition methods to automatic identification of microscopic images of rocks registered under different polarization and lighting conditions , 2013 .

[4]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[5]  Snehamoy Chatterjee.  Vision-based rock-type classification of limestone using multi-class support vector machine , 2012, Applied Intelligence.

[6]  K. Laws.  Textured Image Segmentation , 1980 .

[7]  Christian Koeberl,et al.  Clast size distribution and quantitative petrography of shocked and unshocked rocks from the El'gygytgyn impact structure , 2013 .

[8]  Ari Visa,et al.  Classification of natural rock images using classifier combinations , 2006 .

[9]  R. K. Agrawal,et al.  First and Second Order Statistics Features for Classification of Magnetic Resonance Brain Images , 2012 .

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

[11]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Leena Lepistö,et al.  Rock image classification based on k-nearest neighbour voting , 2006 .

[13]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[14]  Rajat Raina,et al.  Self-taught learning , 2009 .

[15]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[16]  Tara A. Estlin,et al.  AEGIS Automated Science Targeting for the MER Opportunity Rover , 2012, TIST.

[17]  Shigeo Abe,et al.  Comparison of L1 and L2 support vector machines , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[18]  Mariusz Mlynarczuk,et al.  The application of pattern recognition in the automatic classification of microscopic rock images , 2013, Comput. Geosci..

[19]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[20]  Alex Ellery,et al.  Autonomous rock classification using Bayesian image analysis for Rover-based planetary exploration , 2015, Comput. Geosci..

[21]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[22]  T. Estlin,et al.  Experiments in Onboard Rover Traverse Science , 2008, 2008 IEEE Aerospace Conference.

[23]  Tara A. Estlin,et al.  Oasis: Onboard autonomous science investigation system for opportunistic rover science , 2007, J. Field Robotics.

[24]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[25]  Changjing Shang,et al.  Support vector machine-based classification of rock texture images aided by efficient feature selection , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[26]  Feiping Nie,et al.  Robust and Discriminative Self-Taught Learning , 2013, ICML.

[27]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[28]  V. Abhaikumar,et al.  Classification of Rock Textures , 2012 .

[29]  Ari Visa,et al.  Rock image classification using color features in Gabor space , 2005, J. Electronic Imaging.

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

[31]  Peng Wang,et al.  A Comparison of Texture Teatures for the Classification of Rock Images , 2004, IDEAL.

[32]  Cor J. Veenman,et al.  Kernel Codebooks for Scene Categorization , 2008, ECCV.

[33]  Quoc V. Le,et al.  ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning , 2011, NIPS.

[34]  David R. Thompson,et al.  Autonomous Rock Outcrop Segmentation as a Tool for Science and Exploration Tasks in Surface Operations , 2014 .

[35]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[36]  Robert P. W. Duin,et al.  Improving the Maximum-Likelihood Co-occurrence Classifier: A Study on Classification of Inhomogeneous Rock Images , 2005, SCIA.

[37]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[38]  Andrew Y. Ng,et al.  Learning Feature Representations with K-Means , 2012, Neural Networks: Tricks of the Trade.

[39]  E. Mjolsness,et al.  AUTONOMOUS ROCK DETECTION FOR MARS TERRAIN , 2001 .

[40]  Gordon R. Osinski,et al.  A methodology for the semi‐automatic digital image analysis of fragmental impactites , 2014 .