Incremental GRLVQ: Learning relevant features for 3D object recognition

We present a new variant of generalized relevance learning vector quantization (GRLVQ) in a computer vision scenario. A version with incrementally added prototypes is used for the non-trivial case of high-dimensional object recognition. Training is based upon a generic set of standard visual features, the learned input weights are used for iterative feature pruning. Thus, prototypes and input space are altered simultaneously, leading to very sparse and task-specific representations. The effectiveness of the approach and the combination of the incremental variant together with pruning was tested on the COIL100 database. It exhibits excellent performance with regard to codebook size, feature selection and recognition accuracy.

[1]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[2]  Hermann Ney,et al.  Automatic categorization of medical images for content-based retrieval and data mining. , 2005, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[3]  M J Tarr,et al.  Is human object recognition better described by geon structural descriptions or by multiple views? Comment on Biederman and Gerhardstein (1993). , 1995, Journal of experimental psychology. Human perception and performance.

[4]  B. Sendhoff,et al.  Evolution of Hierarchical Features for Visual Object Recognition , 2022 .

[5]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[6]  A. J. Mistlin,et al.  Visual neurones responsive to faces , 1987, Trends in Neurosciences.

[7]  B. S. Manjunath,et al.  Adaptive nearest neighbor search for relevance feedback in large image databases , 2001, MULTIMEDIA '01.

[8]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[10]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[11]  I. T. Jolliffe,et al.  Generalizations and Adaptations of Principal Component Analysis , 1986 .

[12]  Thomas Villmann,et al.  Estimating Relevant Input Dimensions for Self-organizing Algorithms , 2001, WSOM.

[13]  Larry A. Rendell,et al.  The Feature Selection Problem: Traditional Methods and a New Algorithm , 1992, AAAI.

[14]  Geetha Srikantan,et al.  A multiple feature/resolution approach to handprinted digit and character recognition , 1996, Int. J. Imaging Syst. Technol..

[15]  W. Krzanowski Selection of Variables to Preserve Multivariate Data Structure, Using Principal Components , 1987 .

[16]  Ron Kohavi,et al.  Irrelevant Features and the Subset Selection Problem , 1994, ICML.

[17]  Barbara Hammer,et al.  Generalized Relevance LVQ for Time Series , 2001, ICANN.

[18]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[19]  Kurt Hornik,et al.  Artificial Neural Networks — ICANN 2001 , 2001, Lecture Notes in Computer Science.

[20]  Godfried T. Toussaint,et al.  Geometric proximity graphs for improving nearest neighbor methods in instance-based learning and data mining , 2005, Int. J. Comput. Geom. Appl..

[21]  Bir Bhanu,et al.  Probabilistic Feature Relevance Learning for Content-Based Image Retrieval , 1999, Comput. Vis. Image Underst..

[22]  Lakhmi C. Jain,et al.  Bioinformatics using computational intelligence paradigms , 2005 .

[23]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.

[24]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[25]  Michael J. Tarr Is human object recognition better described by geon structural description or by multiple views , 1995 .

[26]  Thomas Villmann,et al.  Supervised Neural Gas with General Similarity Measure , 2005, Neural Processing Letters.

[27]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[28]  Stepán Obdrzálek,et al.  Object Recognition using Local Affine Frames on Distinguished Regions , 2002, BMVC.

[29]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[30]  M.Kleinberg Jon,et al.  Advances in Self-Organizing Maps, 7th International Workshop, WSOM 2009, St. Augustine, FL, USA, June 8-10, 2009. Proceedings , 2009, WSOM.

[31]  Barbara Hammer,et al.  Prototype based recognition of splice sites , 2005 .

[32]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

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

[34]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[35]  H. Deutsch Principle Component Analysis , 2004 .

[36]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[37]  Ali Shokoufandeh,et al.  View-based object recognition using saliency maps , 1999, Image Vis. Comput..

[38]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[39]  Thomas Villmann,et al.  Rule Extraction from Self-Organizing Networks , 2002, ICANN.

[40]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[41]  Yuan Qi,et al.  Predictive automatic relevance determination by expectation propagation , 2004, ICML.

[42]  Helge J. Ritter,et al.  A system for various visual classification tasks based on neural networks , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[43]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  Heiko Wersing,et al.  Rapid Online Learning of Objects in a Biologically Motivated Recognition Architecture , 2005, DAGM-Symposium.

[45]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[46]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[47]  Christos Faloutsos,et al.  Fast Nearest Neighbor Search in Medical Image Databases , 1996, VLDB.

[48]  D. Perrett,et al.  Visual neurones responsive to faces in the monkey temporal cortex , 2004, Experimental Brain Research.

[49]  Karl Sims,et al.  Handwritten Character Classification Using Nearest Neighbor in Large Databases , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[50]  M.M. Van Hulle,et al.  View-based 3D object recognition with support vector machines , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[51]  Simon K. Warfield,et al.  Fast k-NN classification for multichannel image data , 1996, Pattern Recognit. Lett..

[52]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[53]  Thomas Villmann,et al.  Generalized relevance learning vector quantization , 2002, Neural Networks.

[54]  B. Hammer,et al.  Monitoring technical systems with prototype based clustering , 2003 .

[55]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[56]  Alan F. Murray,et al.  Synaptic Rewiring for Topographic Map Formation , 2008, ICANN.