Login | Register

View-based 3D Objects Recognition with Expectation Propagation Learning

Title:

View-based 3D Objects Recognition with Expectation Propagation Learning

Bertrand, Adrien (2016) View-based 3D Objects Recognition with Expectation Propagation Learning. Masters thesis, Concordia University.

[thumbnail of Bertrand_MASc_S2016.pdf]
Preview
Text (application/pdf)
Bertrand_MASc_S2016.pdf - Accepted Version
Available under License Spectrum Terms of Access.
3MB

Abstract

In this thesis, we present an improvement on the Expectation Propagation learning framework, specifically various enhancements on both speed and accuracy. We use this enhanced EP learning with the Inverted Dirichlet mixture model as well as the Dirichlet mixture model, to implement an algorithm to recognize 3D objects. Those objects are in our case from a view-based 3D models database that we have assembled. Following specific rules determined by analyzing the results of our tests, we’ve been able to get good recognition rates. Experimental results are presented with different object classes by comparing recognition rates and confidence level, according to different tuning parameters we’re able to refine towards specific classes for better specialized accuracy.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Concordia Institute for Information Systems Engineering
Item Type:Thesis (Masters)
Authors:Bertrand, Adrien
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Information Systems Security
Date:March 2016
Thesis Supervisor(s):Bouguila, Nizar
ID Code:981025
Deposited By: ADRIEN BERTRAND
Deposited On:15 Jun 2016 16:28
Last Modified:18 Jan 2018 17:52

References:

[1] Daniel Lowd and Pedro Domingos, "Naive Bayes Models for Probability Estimation," in ICML, 2005.
[2] Xiangfei Qian and Cang Ye, "3D Object Recognition by Geometric Context and Gaussian Mixture-Model-Based," in IEEE International Conference on Robotics & Automation, Hong-Kong, 2014.
[3] Kah-Kay Sung and Tomaso Poggio, "Example-Based Learning for View-Based Human Face Detection," IEEE Transactions On Pattern Analysis And Machine Intelligence, vol. 20, no. 1, pp. 39-51, January 1998.
[4] Meng Wang, Yue Gao, Ke Lu, and Yong Rui, "View-Based Discriminative Probabilistic Modeling for 3D Object Retrieval and Recognition," IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 22, no. 4, pp. 1395-1407, Avril 2013.
[5] Christophe Andrieu, Nando De Freitas, Arnaud Doucet, and Michael Jordan, "An Introduction to MCMC for Machine Learning," in Machine Learning., 2003.
[6] Zhihua Zhang et al., "Learning a multivariate Gaussian mixture model with the reversible jump MCMC algorithm," Statistics and Computing, vol. 14, pp. 343-355, 2004.
[7] Sun Min, Su Hao, Savarese S., and Fei-Fei L., "Min, Sun ; Hao, Su ; S., Savarese ; L., Fei-Fei," in Computer Vision and Pattern Recognition, Miami, 2009, pp. 1247-1254.
[8] Cordelia Schmid and Liebelt Joerg, "Multi-View Object Class Detection with a 3D Geometric Model," in Computer Vision & Pattern Recognition, 2010, pp. 1688-1695.
[9] Gu Chunhui and Ren Xiaofeng, "Discriminative Mixture-of-Templates for Viewpoint Classification," Computer Vision - ECCV, vol. 6315, pp. 408-421, 2010.
[10] Derek Hoiem and Silvio Savarese, Representations and Techniques for 3D Object Recognition and Scene Interpretation.: Morgan & Claypool, 2011.
[11] Lian Zhouhui, Godil Afzal, and Sun Xianfang, "Visual Similarity based 3D Shape Retrieval Using Bag-of-Features," in Shape Modeling International Conference (SMI), Aix-en-Provence, 2010, pp. 25-36.
[12] Chen Ding-Yun, Tian Xiao-Pei, Shen Yu-Te, and Ouhyoung Ming, "On Visual Similarity Based 3D Model Retrieval," Computer Graphics Forum, vol. 22, no. 3, pp. 223-232, 2003.
[13] Krishnan Ramnath, Dufipta N Sinha, Richard Szeliski, and Edward Hsiao, "Car Make and Model Recognition using 3D Curve Alignment," in Applications of Computer Vision (WACV), 2014 IEEE Winter Conference, 2014, pp. 1-8.
[14] Louis-Philippe Morency, Ali Rahimi, and Trevor Darrell, "Adaptive view-based appearance models," in Computer Vision and Pattern Recognition - IEEE conference, 2003, pp. 803-810.
[15] Qiong Liu, "A Survey of Recent View-based 3D Model Retrieval Methods," Research report arXiv:1208.3670 [cs.CV], 2012.
[16] Taoufik Bdiri and Nizar Bouguila, "Bayesian learning of inverted Dirichlet mixtures for SVM kernels generation," Neural Computing and Applications, vol. 23, no. 5, pp. 1443-1458, October 2013.
[17] Nizar Bouguila, Djemel Ziou, and Jean Vaillancourt, "Unsupervised Learning of a Finite Mixture Model Based on the Dirichlet Distribution and Its Application," IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 13, no. 11, pp. 1533-1543, Nov. 2004.
[18] Wentao Fan and Nizar Bouguila, "Non-Gaussian Data Clustering via Expectation Propagation Learning of Finite Dirichlet Mixture Models and Applications," Neural Process Letters, vol. 39, no. 2, pp. 115-135, Avril 2014.
[19] Wentao Fan and Nizar Bouguila, "Expectation propagation learning of a Dirichlet process mixture of Beta-Liouville distributions for proportional data clustering," Engineering Applications of Artificial Intelligence, vol. 43, no. C, pp. 1-14, August 2015.
[20] Tom Minka, "Expectation Propagation for Approximate Bayesian Inference," Proceedings of the conference on uncertainty in artificial intelligence (UAI), pp. 362-369, 2001.
[21] George G. Tiao and Irwin Cuttman, "The Inverted Dirichlet Distribution with Applications," Journal of the American Statistical Association, vol. 60, no. 311, pp. 793-805, Sept. 1965.
[22] Manfred Opper, Andre Manoel, and Jack Raymond, Expectation Propagation, 2013.
[23] Zhanyu Ma and Arne Leijon, "Expectation propagation for estimating the parameters of the beta distribution," Proceedings of IEEE international conference on acoustics speech and signal processing (ICASSP), pp. 2082-2085, 2010.
[24] Tom Heskes and Onno Zoeter, "Expectation propagation for approximate inference in dynamic Bayesian networks," Proceedings of the conference on uncertainty in artificial intelligence (UAI), pp. 216-223, 2002.
[25] Miguel A. Carreira-Perpiñán, "Mode-Finding for Mixtures of Gaussian Distributions," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1318-1323, November 2000.
[26] Bruce Fielitz and Buddy Myers, "Estimation of parameters in the Beta distribution," Decision Sciences, vol. 6, pp. 1-13, 1975.
[27] INRIA GAMMA Group. (2013, November) 3D Meshes Research Database. [Online]. https://www.rocq.inria.fr/gamma/gamma/download/download.php

[28] Various authors for "The Free 3D Models". (2015) Vehicles 3D Models - Free 3D Vehicles download. [Online]. http://tf3dm.com/3d-models/vehicles

[29] Various authors for 3dmodelfree.com. (2015) Transport 3D Models Downloads. [Online]. http://www.3dmodelfree.com/3dmodel/list420-1.htm

[30] Stephen Yoo and Vorobyov Vorobyov. (2011, August) Binary Shape Clustering via Zernike Moments. [Online]. http://www.math.uci.edu/icamp/summer/research_11/vorobyov/ZM.pdf

[31] P. F. Krekel, "Zernike Moments and Rotation Invariant Object Recognition: A Neural Network Oriented Case Study," TNO-Physics and Electronics Laboratory, 1992.
[32] Geoffrey Irving. (2008, December) Stack Overflow - Enabling floating point interrupts on Mac OS X Intel. [Online]. http://stackoverflow.com/a/340683/378298

[33] Jay Conrod. (2010, May) jayconrod.com - Trapping floating point exceptions in Linux. [Online]. http://jayconrod.com/posts/33/trapping-floating-point-exceptions-in-linux

[34] Manuel Gil, Fady Alajaji, and Tamas Linder, "Rényi divergence measures for commonly used univariate continuous distributions," Information Sciences, vol. 249, pp. 124-131, November 2013.
[35] Don H. Johnson and Sinan Sinanovic, "Symmetrizing the Kullback-Leibler Distance," IEEE Transactions on Information Theory, 2000. [Online]. http://www.ece.rice.edu/~dhj/resistor.pdf

[36] Karel Zuiderveld, "Contrast limited adaptive histogram equalization," Graphics gems IV, pp. 474-485, 1994.
[37] Aki Vehtari, Pasi Jylnki, Christian Robert, Nicolas Chopin, John P. Cunningham Andrew Gelman. (2014, December) arxiv - Expectation propagation as a way of life. [Online]. http://arxiv.org/abs/1412.4869

[38] NVIDIA. (2016) NVIDIA DRIVE PX. [Online]. https://www.nvidia.com/object/drive-px.html

[39] Manfred Opper, Ulrich Paquet, and Ole Winther, "Improving on Expectation Propagation," Advances in Neural Information Processing Systems, no. 21, pp. 1241-1248, 2008.
[40] Vladimir Sacek. (2006, July) Telescope Optics. [Online]. http://www.telescope-optics.net/monochromatic_eye_aberrations.htm

[41] Laurent Ribon. (2011) GLC_Player -- Documentation : Multi Captures. [Online]. http://glc-player.net/doc.php?page=multiCaptures

[42] Michael Boland, Tom Macura, Lior Shamir, and Ilya Shamir. (2012, December) Zernike moment generating function. [Online]. https://wnd-charm.googlecode.com/svn-history/r230/wndchrm/branches/feature-timing/textures/zernike/zernike2.cpp
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top