Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published February 1998 | public
Journal Article

Learning to Recognize Volcanoes on Venus


Dramatic improvements in sensor and image acquisition technology have created a demand for automated tools that can aid in the analysis of large image databases. We describe the development of JARtool, a trainable software system that learns to recognize volcanoes in a large data set of Venusian imagery. A machine learning approach is used because it is much easier for geologists to identify examples of volcanoes in the imagery than it is to specify domain knowledge as a set of pixel-level constraints. This approach can also provide portability to other domains without the need for explicit reprogramming; the user simply supplies the system with a new set of training examples. We show how the development of such a system requires a completely different set of skills than are required for applying machine learning to "toy world" domains. This paper discusses important aspects of the application process not commonly encountered in the "toy world" including obtaining labeled training data, the difficulties of working with pixel data, and the automatic extraction of higher-level features.

Additional Information

© 1998 Kluwer Academic Publishers. Received March 4, 1997, Accepted September 18, 1997, Final Manuscript November 15, 1997. The research described in this article has been carried out in part by the Jet Propulsion Laboratory, California Institute of Technology, under contract with the National Aeronautics and Space Administration. Support was provided by the NASA Office of Advanced Concepts and Technology (OACT - Code CT), a JPL DDF award, NSF research initiation grant IRI 9211651, and a grant from the Swedish Foundation for International Cooperation in Research and Higher Education (Lars Asker). We would like to thank Michael Turmon for his help and for performing some of the experiments. We would also like to thank Saleem Mukhtar, Maureen Burl, and Joe Roden for their help in developing the software and user-interfaces. The JARtool graphical user interface is built on top of the SAOtng image analysis package developed at the Smithsonian Astrophysical Society (Mendel et al., 1997).

Additional details

August 19, 2023
October 26, 2023