Steering seismic texture analysis algorithms using expert input

Patent metadata

Field	Value
Publication number	US-10121096-B2
Application number	US-201615223777-A
Country	US
Kind code	B2
Filing date	Jul 29, 2016
Priority date	Jul 29, 2016
Publication date	Nov 6, 2018
Grant date	Nov 6, 2018

Abstract

A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.

First claim

What is claimed is:

1. A method, comprising:
displaying an image comprising seismic data on a display of a device;
detecting, by a processor of the device, user input corresponding to one or more portions of the image, wherein the user input is descriptive of the seismic data;
causing, by the processor of the device, the image to be analyzed to determine a first feature vector corresponding to the seismic data;
causing, by the processor of the device, the user input to be analyzed to determine at least one further feature vector corresponding to the user input; and
determining at least one seismic texture for at least the one or more portions of the image based on the first feature vector and the at least one further feature vector.

2. The method of claim 1 , wherein the user input comprises at least one of: at least one sketch input corresponding to one of the portions of the image on the display, and at least one textual description input corresponding to one of the portions of the image on the display; and wherein the at least one further feature vector comprises a second feature vector for the at least one sketch and/or a third feature vector for the at least one textual description.

3. The method of claim 2 , wherein determining the at least one seismic texture for the one or more portions of the image is based at least on the second feature vector and the third feature vector.

4. The method of claim 2 , wherein:
the second feature vector represents a set of features corresponding to at least a portion of the at least one sketch.

5. The method of claim 4 , wherein the set of features corresponding to at least the portion of the at least one sketch comprises at least one of: a straight line length, an angle, free-form arc length, or an area between a stroke and a straight line approximation.

6. The method of claim 2 , wherein the at least one textual description input is a natural language description input, and wherein the third feature vector is determined using at least one of: a bag of words corresponding to the natural language description input, and word vectors corresponding to the natural language description input.

7. The method of claim 1 , the method further comprising:
displaying labels for the one or more portions of the image based on the determined at least one seismic texture.

8. The method of claim 1 , the method further comprising:
storing the user input and the determined at least one seismic texture in a database.

9. The method of claim 8 , the method further comprising:
determining at least one further seismic texture for one or more portions of another image based at least on the user input stored in the database.

10. An apparatus comprising:
at least one processor; and
at least one non-transitory memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
display an image comprising seismic data on a display of the apparatus;
detect, by the at least one processor, a user input corresponding to one or more portions of the image;
cause, by the at least one processor, the image to be analyzed to determine a first feature vector corresponding to the seismic data;
cause, by the at least one processor, the user input to be analyzed to determine at least one further feature vector corresponding to the user input; and
determine at least one seismic texture for the one or more portions of the image based at least on the first feature vector and the at least one further feature vector.

11. The apparatus of claim 10 , wherein the user input comprises at least one of: at least one sketch input corresponding to one of the portions of the image on the display, and at least one textual description input corresponding to one of the portions of the image on the display; and wherein the at least one further feature vector comprises a second feature vector for the at least one sketch and/or a third feature vector for the at least one textual description.

12. The apparatus of claim 11 , wherein determination of the at least one seismic texture for the one or more portions of the image is based at least on the second feature vector and the third feature vector.

13. The apparatus of claim 11 , wherein:
the second feature vector represents a set of features corresponding to at least a portion of the at least one sketch.

14. The apparatus of claim 13 , wherein the set of features corresponding to at least the portion of the at least one sketch comprises at least one of: a straight line length, an angle, free-form arc length, or an area between a stroke and a straight line approximation.

15. The apparatus of claim 11 , wherein the at least one textual description input is a natural language description input, and wherein the third feature vector is determined using at least one of: a bag of words corresponding to the natural language description input, and word vectors corresponding to the natural language description input.

16. The apparatus of claim 10 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to:
displaying labels for the one or more portions of the image based on the determined at least one seismic texture.

17. The apparatus of claim 10 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to:
storing the user input and the determined at least one seismic texture in a database.

18. The apparatus of claim 17 , wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to:
determine at least one further seismic texture for one or more portions of another image based at least on the user input stored in the database.

19. A computer program product for analyzing an image, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:
display the image on a display, wherein the image comprises seismic data;
detect, using a processor, a user input corresponding to one or more portions of the image;
cause, using the processor, the image to be analyzed to determine a first feature vector corresponding to the seismic data;
cause, using the processor, the user input to be analyzed to determine at least one further feature vector corresponding to the user input; and
determine, using the processor, at least one seismic texture for at least the one or more portions of the image based on the first feature vector and the at least one further feature vector.

Assignees

• IBM

Inventors

• Binotto Alecio Pedro Delazari
• Brazil Emilio Ashton Vital
• De Gusmao Cerqueira Renato Fontoura
• Da Silva Ferreira Rodrigo
• Moreno Michael Raghib
• De Santana Vagner Figueredo
• Da Silva Viviane Torres

Classifications

• G06V10/945

  User interactive design; Environments; Toolboxes · CPC title

• G06V30/19173

  Classification techniques · CPC title

• G06V10/54 Primary

  relating to texture · CPC title

• G06F40/169

  Annotation, e.g. comment data or footnotes · CPC title

• G06F18/24

  Classification techniques · CPC title