Chroma Energy, Inc.

Chroma Graphics, Inc.

Chroma Group, Inc.

Peter Whitehead

Robert Wentland

Bradley C Wallet

Dennis M Johnson

Fredric S Young

Jawad Mokhtar

Frederic S Young

An apparatus and method for analyzing known data, and storing the known data in a pattern database ('PDB') as a template is provided. Additional methods are provided for comparing target data against the templates in the PDB. The data is stored in such a way as to facilitate the visual recognition of desired patterns or indicia indicating the presence of a desired or undesired feature within the new data. The apparatus and method is applicable to a variety of applications where large amounts of information are generated, and/or if the data exhibits fractal or chaotic attributes.

Pattern recognition applied to graphic imaging

A system, method and apparatus are provided for applying templates to find deposits of oil and natural gas. A personal computer is used to perform calculations on known data to generate hyperdimensional templates that are stored within a pattern database. The hyperdimensional templates are generated in a layered series of cutting, attributing, and statisizing phases using data known to represent existing oil and gas reservoirs. The hyperdimensional templates are stored in a pattern database. The templates are used in comparison to target data sets in order to detect patterns that are consistent with reserves of oil and/or natural gas.

Pattern recognition template application applied to oil exploration and production

An apparatus and method for analyzing known data, storing the known data in a pattern database ('PDB') as a template is provided. Additional methods are provided for comparing new data against the templates in the PDB. The data is stored in such a way as to facilitate the visual recognition of desired patterns or indicia indicating the presence of a desired or undesired feature within the new data. The apparatus and method is applicable to a variety of applications where large amounts of information are generated, and/or if the data exhibits fractal or chaotic attributes.

Pattern recognition applied to oil exploration and production

An apparatus, system, and set of methods are provided for building templates that can be used in the exploration and production oil and gas deposits. A personal computer is used to perform calculations on known data to generate hyperdimensional templates that are stored within a pattern database. The hyperdimensional templates are generated in a layered series of cutting, attributing, and statisizing phases using data known to represent existing oil and gas reservoirs. The hyperdimensional templates are stored in a pattern database. Methods are provided for identifying misclassifications and otherwise determine the quality of the templates in the pattern database.

Pattern recognition template construction applied to oil exploration and production

A method and apparatus are provided to process spatial data including seismic data. Given a spatial dataset of n dimensions, a data-driven partitioning of the dataset is effected into topographically contiguous regions using feature specific indices. Then on each region, a set of features is calculated according to a computer process, 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 an analytical structure to be input to a classifier.

Method and apparatus for extracting selected feature information and classifying heterogeneous regions of n-dimensional spatial data

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.

Growing community of inventors

San Rafael, CA, United States of America

Peter Whitehead