Method and apparatus for extracting selected feature information and classifying heterogeneous regions of N-dimensional spatial data
US6363327B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | May 2, 2000 |
| Grant date | Mar 26, 2002 |
| Priority date | — |
| Expiry date | May 2, 2020 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG01V1/30
- WIPO fieldMeasurement
- WIPO sectorInstruments
Abstract
Given a spatial dataset of n dimensions, a data-driven partitioning of the dataset is effected into topographically contiguous regions using feature specific indices (for example, by examining the change in polarity of the impedance of seismic data). Then on each region, a set of features (which may be mathematical functions) is calculated (e.g., mean value of all data in the region), wherein the features are considered sufficiently descriptive of the region. Thereupon, two or more regions which are topographically contiguous are grouped together and the associated features are assembled in a structure (e.g., a vector or a matrix) to be input to a classifier.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.