CaltechAUTHORS
  A Caltech Library Service

Learning to Recognize Volcanoes on Venus

Burl, Michael C. and Asker, Lars and Smyth, Padhraic and Fayyad, Usama and Perona, Pietro and Crumpler, Larry and Aubele, Jayne (1998) Learning to Recognize Volcanoes on Venus. Machine Learning, 30 (2-3). pp. 165-194. ISSN 0885-6125. https://resolver.caltech.edu/CaltechAUTHORS:20140730-101721831

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20140730-101721831

Abstract

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.


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1023/A:1007400206189DOIArticle
https://rdcu.be/btmg2PublisherFree ReadCube access
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
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).
Funders:
Funding AgencyGrant Number
NASA/JPL/CaltechUNSPECIFIED
NSFIRI-9211651
Swedish Foundation for International Cooperation in Research and Higher Education (STINT)UNSPECIFIED
Subject Keywords:machine learning pattern recognition learning from examples large image databases data mining automatic cataloging detection of natural objects Magellan SAR JARtool volcanoes Venus principal components analysis trainable
Issue or Number:2-3
Record Number:CaltechAUTHORS:20140730-101721831
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20140730-101721831
Official Citation:Burl, M.C., Asker, L., Smyth, P. et al. Machine Learning (1998) 30: 165. https://doi.org/10.1023/A:1007400206189
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47634
Collection:CaltechAUTHORS
Deposited By: Caroline Murphy
Deposited On:08 Aug 2014 23:52
Last Modified:03 Oct 2019 06:55

Repository Staff Only: item control page