Robust shape classification

Abstract We consider the problem of classifying objects using their two dimensional silhouettes in environments generating large aberrant observations (outliers). These may be generated by failures in edge extraction or long tailed imaging noise. We propose a new approach based on circular sub-set autoregressions with robust parameter estimation and novel lag selection procedures. Lag selection is carried out in the test and training sets. The resulting estimates of the spectral function are used in a ‘distance’ based classifier which substantially out-performs techniques based on the sample covariance function in outlier contaminated data. This algorithm also out-performs a robust analogue of Dubois and Glanz (1986), and is well suited to classification problems where sensitivity to clutter is important. Typical examples are fault identification or the recognition of new objects entering a domain.

[1]  Adam J. Efron,et al.  Detection in impulsive noise based on robust whitening , 1994, IEEE Trans. Signal Process..

[2]  R. Terrell,et al.  PROJECTION MODULUS: A NEW DIRECTION FOR SELECTING SUBSET AUTOREGRESSIVE MODELS , 1997 .

[3]  Jie Chen,et al.  Affine curve moment invariants for shape recognition , 1997, Pattern Recognit..

[4]  R. L. Kashyap,et al.  Robust Image Models and Their Applications , 1988 .

[5]  Classification Of Textures Using Second‐Order Spectra , 1992 .

[6]  C. Hurvich,et al.  High Breakdown Methods of Time Series Analysis , 1993 .

[7]  Richard H. Glendinning,et al.  Signal plus noise models in shape classification , 1994, Pattern Recognit..

[8]  Manohar Das,et al.  A Bivariate Autoregressive Technique for Analysis and Classification of Planar Shapes , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  R. H. Shumway,et al.  1 Discriminant analysis for time series , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[10]  Jean-Pierre Antoine,et al.  Shape characterization with the wavelet transform , 1997, Signal Process..

[11]  Michael J. Black,et al.  The outlier process: unifying line processes and robust statistics , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Wen-Tsuen Chen,et al.  A stochastic representation of cursive Chinese characters for on-line recognition , 1997, Pattern Recognit..

[13]  Elvezio Ronchetti,et al.  Robust Linear Model Selection by Cross-Validation , 1997 .

[14]  J. Alagón.  SPECTRAL DISCRIMINATION FOR TWO GROUPS OF TIME SERIES , 1989 .

[15]  Roland T. Chin,et al.  On modelling, extraction, detection and classification of deformable contours from noisy images , 1998, Image Vis. Comput..

[16]  R. R. Hansen,et al.  Empirical robust estimators for 2D noncausal autoregressive models , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[17]  Kie B. Eom.  Shape recognition using spectral features , 1998, Pattern Recognit. Lett..

[18]  Neri Merhav,et al.  Robust methods for model order estimation , 1996, IEEE Trans. Signal Process..

[19]  Lalit Gupta,et al.  Robust partial shape classification using invariant breakpoints and dynamic alignment , 1990, Pattern Recognit..

[20]  Abhinanda Sarkar,et al.  Shape Description by Time Series , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Kie B. Eom,et al.  Shape recognition by a scale-invariant model , 1991, J. Syst. Integr..

[22]  N. Mohankrishnan,et al.  Shape recognition using a nonstationary autoregressive hidden Markov model , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[23]  D. Huang,et al.  Some variable selection procedures in multivariate linear regression models , 1994 .

[24]  Yang He,et al.  2-D Shape Classification Using Hidden Markov Model , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Aldo Cumani,et al.  Recovering the 3D structure of tubular objects from stereo silhouettes , 1997, Pattern Recognit..

[26]  V. Yohai,et al.  4 Robustness in time series and estimating ARMA models , 1985 .

[27]  Petar M. Djuric,et al.  Model selection based on Bayesian predictive densities and multiple data records , 1994, IEEE Trans. Signal Process..

[28]  Bir Bhanu,et al.  A system for model-based object recognition in perspective aerial images , 1998, Pattern Recognit..

[29]  Masanobu Taniguchi,et al.  Nonparametric approach for discriminant analysis in time series , 1995 .

[30]  T. Davies,et al.  Sewer pipe deformation assessment by image analysis of video surveys , 1998, Pattern Recognit..

[31]  George Papadourakis,et al.  Object recognition using invariant object boundary representations and neural network models , 1992, Pattern Recognit..

[32]  Manohar Das,et al.  Nonstationary autoregressive modeling of object contours , 1992, IEEE Trans. Signal Process..

[33]  David Pycock,et al.  Robust statistical models for cell image interpretation , 1997, Image Vis. Comput..

[34]  Mohammad V. Malakooti,et al.  CARMA Model method of two-dimensional shape classification: An eigensystem approach vs. the LP norm , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[35]  Jian Li,et al.  Efficient mixed-spectrum estimation with applications to target feature extraction , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[36]  Yurij S. Kharin.  Robustness in Discriminant Analysis , 1996 .

[37]  Filson H. Glanz,et al.  An Autoregressive Model Approach to Two-Dimensional Shape Classification , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  P. Kanjilal,et al.  On a method of identification of best subset model from full ar-model , 1995 .

[39]  Takio Kurita,et al.  Complex Autoregressive Model for Shape Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  José A. García,et al.  An autoregressive curvature model for describing cartographic boundaries , 1995 .

[41]  Shyamal Das Peddada,et al.  An automated algorithm for cleaning and ordering the boundary points of a one-dimensional curve in a segmented image , 1998, IEEE Trans. Geosci. Remote. Sens..

[42]  Takio Kurita,et al.  Invariant distance measures for planar shapes based on complex autoregressive model , 1994, Pattern Recognit..

[43]  Rama Chellappa,et al.  Stochastic models for closed boundary analysis: Representation and reconstruction , 1981, IEEE Trans. Inf. Theory.

[44]  S. Heiler,et al.  RECURSIVE GENERALIZED M ESTIMATES FOR AUTOREGRESSIVE MOVING-AVERAGE MODELS , 1992 .

[45]  H. A. Karlsen,et al.  Autoregressive segmentation of signal traces with applications to geological dipmeter measurements , 1990 .

[46]  I. D. Hill,et al.  Correction: Algorithm AS 183: An Efficient and Portable Pseudo-Random Number Generator , 1982 .

[47]  Lorenzo Bruzzone,et al.  Structured neural networks for signal classification , 1998, Signal Process..

[48]  Matti Pietikäinen,et al.  An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[49]  D. Thomson,et al.  Robust-resistant spectrum estimation , 1982, Proceedings of the IEEE.

[50]  Malcolm C. Thomas,et al.  Sand grain analysis—image processing, textural algorithms and neural nets , 1998 .

[51]  Robert H. Shumway,et al.  Discrimination and Clustering for Multivariate Time Series , 1998 .

[52]  Ben Pinkowski.  Multiscale fourier descriptors for classifying semivowels in spectrograms , 1993, Pattern Recognit..

[53]  P. Laycock,et al.  SPECTRAL RATIO DISCRIMINANTS AND INFORMATION THEORY , 1981 .

[54]  P. Broersen.  Selecting subsets of autoregressive parameters , 1990 .

[55]  Alan C. Bovik,et al.  Robust techniques for edge detection in multiplicative weibull image noise , 1990, Pattern Recognit..

[56]  Shun-ichi Amari,et al.  Differential-geometrical methods in statistics , 1985 .

[57]  I. D. Hill,et al.  An Efficient and Portable Pseudo‐Random Number Generator , 1982 .

[58]  Jammie H. Penm,et al.  THE RECURSIVE FITTING OF SUBSET VARX MODELS , 1993 .