Knowledge Discovery in an Object-Oriented Oceanographic Database System
Abstract
The rate at which scientific data is collected today has overwhelmed the ability of scientists to store and analyze the data. This report describes the results of a three year effort in the development of a knowledge discovery system for use by oceanographers at the Naval Oceanographic Office (NAVOCEANO) at the Stennis Space Center in the identification of provinces of interest in the ocean floor from acoustic imagery. The system is composed of a knowledge discovery component built to interact with a database system currently in use at Stennis Space Center. The knowledge discovery system applies machine learning techniques to features extracted from sonar images to identify provinces of the ocean floor based on visual texture. This requires that the images be segmented into regions of homogeneous texture using a region-growing technique, that features describing the texture of these regions be extracted, that machine learning techniques be applied to classify the regions, that classified images be constructed for visualizing the results, and that the classified images be combined and geo-referenced using a mosaic procedure. NAVOCEANO is currently supporting efforts to integrate the software developed from this project with their image analysis system.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 14, 2000
- Accession Number
- ADA378406
Entities
People
- Julia Hodges
- Susan Bridges
Organizations
- Mississippi State University