IMAGE FEATURE EXTRACTION

Patent №

US 7,203,342

Granted

2007-04-10

Filed 2002

Owner

SCHLUMBERGER TECHNOLOGY CORPORATION

Lab

AI components

2

ml · vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

10081603

A method of extracting desired features from a cellular image including the steps of: (a) selecting an initial cell within the image; (b) selecting an additional cell, near the initial cell, appearing to be associated with a desired feature; (c) repeating step (b) for further cells, near at least one of the previously selected cells, appearing to be associated with said feature, until selection termination criteria are satisfied; and (d) repeating steps (a) through (c) for other initial cells. The method is particularly adept at extracting relatively weakly defined features in relatively noisy images, such as extracting faults or geologic horizons from 2D or 3D seismic data. A method of editing/filtering the features utilizing a stereo net is also disclosed. Related computer system and computer program products for implementing the method are also described.

Machine learningVisionG01V 1/30G06T 7/11G06T 7/12G06T 7/181G06V 10/267G06V 10/457G06V 20/695G06T 2207/10072+7 more

AI classification

Vision1.00
Machine learning1.00
AI hardware0.08
Evolutionary computation0.00
Knowledge representation0.00
Planning0.00
Natural language0.00
Speech0.00

Ownership

SCHLUMBERGER TECHNOLOGY CORPORATION

assignment · 126380225

Assignors

PEDERSEN, STEIN INGE

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC