Structure preserving dimensionality reduction for visual object recognition

Robust object recognition has drawn increasing attention in the field of computer vision and machine learning with fast development in feature extraction and classification techniques, and release of public datasets, such as Caltech datasets, Pascal Visual Object Classes, and ImageNet. Recently, deep learning based object recognition systems have shown significant performance improvements in visual object recognition tasks using innovative learning methodology. However, high dimensional space searching and recognition is time consuming, so performing point and range queries in high dimension is reconsidered for object recognition. This paper proposes optimized dimensionality reduction using structured sparse principle component analysis. The proposed method retains high dimensional feature structures, removes redundant features that do not contribute to similarity, and classifies the query image in a large database. The qualitative and quantitative experimental results, including a comparison with the current state-of-the-art visual object recognition algorithms, verify that the proposed recognition algorithm performs favorably in reducing the query image dimension and number of training images.

[1]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[2]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[3]  Luca Maria Gambardella,et al.  High-Performance Neural Networks for Visual Object Classification , 2011, ArXiv.

[4]  Marc'Aurelio Ranzato,et al.  Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition , 2010, ArXiv.

[5]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  Heiko Hoffmann,et al.  Kernel PCA for novelty detection , 2007, Pattern Recognit..

[8]  R. Tibshirani,et al.  Sparse Principal Component Analysis , 2006 .

[9]  Junzhou Huang,et al.  Learning with structured sparsity , 2009, ICML '09.

[10]  Allen Y. Yang,et al.  Informative feature selection for object recognition via Sparse PCA , 2011, 2011 International Conference on Computer Vision.

[11]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[12]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[14]  Kilian Q. Weinberger,et al.  Unsupervised Learning of Image Manifolds by Semidefinite Programming , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[15]  Michael K. Ng,et al.  Subspace clustering with automatic feature grouping , 2015, Pattern Recognit..

[16]  H. Akaike.  Factor analysis and AIC , 1987 .

[17]  Yuantao Gu,et al.  Greedy pursuits: Stability of recovery performance against general perturbations , 2012, 2012 International Conference on Computing, Networking and Communications (ICNC).

[18]  Edward J. Delp,et al.  Optimum color spaces for skin detection , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[19]  Francis R. Bach,et al.  Structured Variable Selection with Sparsity-Inducing Norms , 2009, J. Mach. Learn. Res..

[20]  Francis R. Bach,et al.  Structured Sparse Principal Component Analysis , 2009, AISTATS.

[21]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[22]  David G. Lowe,et al.  Multiclass Object Recognition with Sparse, Localized Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[23]  Karim Faez,et al.  Chaotic target representation for robust object tracking , 2017, Signal Process. Image Commun..

[24]  Junzhou Huang,et al.  Automatic Image Annotation and Retrieval Using Group Sparsity , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  Wen Gao,et al.  Group-sensitive multiple kernel learning for object categorization , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[26]  Reinaldo Sanchez Arias.  A Convex Optimization Algorithm For Sparse Representation And Applications In Classification Problems , 2013 .

[27]  Kilian Q. Weinberger,et al.  An Introduction to Nonlinear Dimensionality Reduction by Maximum Variance Unfolding , 2006, AAAI.

[28]  Te-Won Lee,et al.  Independent Component Analysis , 1998, Springer US.

[29]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[31]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

[32]  David Zhang,et al.  A Survey of Sparse Representation: Algorithms and Applications , 2015, IEEE Access.

[33]  Yihong Gong,et al.  Linear spatial pyramid matching using sparse coding for image classification , 2009, CVPR.

[34]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[35]  Robin Sibson,et al.  What is projection pursuit , 1987 .

[36]  Mario Fernando Montenegro Campos,et al.  Sparse Spatial Coding: A novel approach for efficient and accurate object recognition , 2012, 2012 IEEE International Conference on Robotics and Automation.

[37]  Junzhou Huang,et al.  The Benefit of Group Sparsity , 2009 .

[38]  Dieter Fox,et al.  Multipath Sparse Coding Using Hierarchical Matching Pursuit , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Qinghua Hu,et al.  Subspace clustering guided unsupervised feature selection , 2017, Pattern Recognit..

[40]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[41]  Thomas Serre,et al.  Object recognition with features inspired by visual cortex , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[42]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[43]  Yihong Gong,et al.  Locality-constrained Linear Coding for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[44]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[45]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[46]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[47]  Mahesan Niranjan,et al.  Exploitation of Machine Learning Techniques in Modelling Phrase Movements for Machine Translation , 2011, J. Mach. Learn. Res..

[48]  Jean Ponce,et al.  Learning mid-level features for recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[49]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[50]  Alfred O. Hero,et al.  Efficient learning of sparse, distributed, convolutional feature representations for object recognition , 2011, 2011 International Conference on Computer Vision.

[51]  Vincent Frouin,et al.  Structured Sparse Principal Components Analysis With the TV-Elastic Net Penalty , 2016, IEEE Transactions on Medical Imaging.