Method and system for using an artificial neural net for image map processing

• US 5,956,701 A
• Filed: 06/13/1997
• Issued: 09/21/1999
• Est. Priority Date: 06/13/1997
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Habermehl, Paul Robert
• Primary Examiner(s): Downs, Robert W.
• Application Number:
  US08/874,530
• Time in Patent Office: 830 Days
• Field of Search: 706/20, 706/27, 706/16
• US Class Current: 706/20
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/20092 Interactive image processing based on input by user
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling

Abstract

The present invention provides a method and system for processing an image, the method comprising the steps of providing an image and specifying a portion of the image. The present invention also includes utilizing an artificial neural net to associate the portion of the image with an application, wherein a plurality of positions are selected within the specified portion of the image.

Claims

1. A method for processing an image, the method comprising the steps of:

a) providing an image;

b) specifying a portion of the image to be associated with an application; and

c) utilizing an artificial neural net to define the portion of the image, wherein a plurality of positions are selected within the portion of the image and wherein the artificial neural net uses the plurality of positions to define the portion of the image.

2. The method of claim 1, wherein the artificial neural net receives information related to the plurality of positions to provide a boundary for the portion of the image.

3. The method of claim 2, wherein the plurality of positions are selected by clicking a pointing device.

4. The method of claim 2, wherein the plurality of positions are selected by scribbling a pointing device.

5. The method of claim 1, wherein the application is accessed via an internet.

6. The method of claim 1, wherein the association is a software link.

7. A system for using an artificial neural net for image map processing, the system comprising:

a display for displaying an image, the image including a portion to be associated with an application, the portion including a plurality of positions;

a processor coupled to the display;

a server which can be coupled with the processor, the server including an artificial neural net which can be trained to define the portion of the image using the plurality of positions.

8. The system of claim 7, wherein the plurality of positions are selected by clicking a pointing device.

9. The system of claim 7, wherein the plurality of positions are selected by scribbling a pointing device.

10. The system of claim 7, wherein the application is accessed via an internet.

11. The system of claim 7, wherein the association is a software link.

12. A method for processing an image, the method comprising the steps of:

a) providing an image;

b) specifying a portion of the image to be linked with information via an internet; and

c) utilizing an artificial neural net to define the portion of the image, wherein a plurality of positions are selected within the specified portion of the image and wherein the artificial neural net uses the plurality of positions to define the portion of the image.