Image database exploration: progress and challenges

In areas as diverse as remote sensing, astronomy, and medical imaging, image acquisition technology has undergone tremendous improvements in recent years in terms of imaging resolution, hardware miniaturization, and computational speed. For example, current and future near-earth and planetary observation systems will return vast amounts of scientific data, a potential treasure-trove for scientific investigation and analysis. Unfortunately, advances in our ability to deal with this volume of data in an effective manner have not paralleled the hardware gains. While special-purpose tools for particular applications exist, there is a dearth of useful general-purpose software tools and algorithms which can assist a scientist in exploring large scientific image databases. At JPL we are currently developing interactive semi-automated image database exploration tools based on pattern recognition and machine learning technology. In this paper we discuss the general problem of automated image database exploration, the particular aspects of image databases which distinguish them from other databases, and how this impacts the application of off-the-shelf learning algorithms to problems of this nature. Current progress will be illustrated using two large-scale image exploration projects at JPL. The paper concludes with a discussion of current and future challenges.

[1]  John A. Richards,et al.  Remote Sensing Digital Image Analysis , 1986 .

[2]  U. Grenander,et al.  Structural Image Restoration through Deformable Templates , 1991 .

[3]  David L. Crawford,et al.  Instrumentation in Astronomy VI , 1986 .

[4]  M I Miller,et al.  Mathematical textbook of deformable neuroanatomies. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Usama Fayyad,et al.  Automated analysis of a large-scale sky survey: the SKICAT system , 1993 .

[6]  Stephen B. Vardeman,et al.  Contextual classification of multispectral image data , 1981, Pattern Recognit..

[7]  Pierre A. Devijver,et al.  Learning the parameters of a hidden Markov random field image model: A simple example , 1987 .

[8]  Usama M. Fayyad,et al.  The Attribute Selection Problem in Decision Tree Generation , 1992, AAAI.

[9]  Matthew Self,et al.  Bayesian Classification , 1988, AAAI.

[10]  Christian Genest,et al.  Combining Probability Distributions: A Critique and an Annotated Bibliography , 1986 .

[11]  Usama M. Fayyad,et al.  SKICAT: A Machine Learning System for Automated Cataloging of Large Scale Sky Surveys , 1993, ICML.

[12]  R. Cooke.  Experts in Uncertainty: Opinion and Subjective Probability in Science , 1991 .

[13]  U. Fayyad.  On the induction of decision trees for multiple concept learning , 1991 .

[14]  Donna J. Peuquet,et al.  Geographic Information Systems and remote sensing. , 1983 .

[15]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  David Green,et al.  Statistical inference for spatial processes , 1990 .

[17]  J. Aubele,et al.  Small domes on Venus: Characteristics and origin , 1990 .

[18]  JoBea Way,et al.  The evolution of synthetic aperture radar systems and their progression to the EOS SAR , 1991, IEEE Trans. Geosci. Remote. Sens..

[19]  P. Burrough.  Principles of Geographical Information Systems for Land Resources Assessment , 1986 .

[20]  B. Ripley.  Statistical inference for spatial processes , 1990 .

[21]  G. Pettengill,et al.  Magellan: Radar Performance and Data Products , 1991, Science.

[22]  Rama Chellappa,et al.  Unsupervised segmentation of polarimetric SAR data using the covariance matrix , 1992, IEEE Trans. Geosci. Remote. Sens..

[23]  Padhraic Smyth,et al.  Detecting Novel Classes with Applications to Fault Diagnosis , 1992, ML.