System and Method for Compiling Images from a Database and Comparing the Compiled Images with Known Images

• US 20110013843A1
• Filed: 07/16/2010
• Published: 01/20/2011
• Est. Priority Date: 12/21/2000
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated (Kyndryl Holdings, Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Seeber, René
• Granted Patent: US 8,107,739 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A method and system for discovering from a database an object which is confusingly similar with a known object. A database, such as the internet, is searched for objects which, when discovered, may be duplicated and stored. A determination is then made if any object from the database is confusingly similar with a known object. A computer-readable storage medium storing program for causing a processing system to perform the steps of duplicating objects from a database to produce duplicated objects; storing the duplicated produce to produce stored duplicated objects; and determining if any stored duplicated object is confusingly similar with a known object.

Claims

1. A computer program product for determining if a web page includes a trademark that is similar to an authentic trademark, the computer program product comprising:

a computer readable storage device(s);

a web crawler program to identify the web page by progressing through hyperlinks;

first program instructions to identify and recognize, by optical character recognition, characters of a text portion of the trademark on the web page;

second program instructions to compare the recognized characters of the trademark on the web page to corresponding characters of the authentic trademark to determine a degree of text match;

third program instructions to compare a template representing a graphical, logo portion of the authentic trademark to a corresponding graphical, logo portion of the trademark on the web page to determine a degree of graphical match; and

fourth program instructions to determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match and the degree of text match; and

wherein

the first, second, third and fourth program instructions and the web crawler program are stored on the computer readable storage device(s).

2. The computer program product of claim 1 wherein:

the template is based on a gray scale representation of the graphical, logo portion of the authentic trademark;

the graphical, logo portion of the trademark on the web page is in red-green-blue color; and

the third program instructions convert the graphical, logo portion of the trademark on the web page from red-green-blue color to a gray scale, and compare the template to the gray-scale converted graphical, logo portion of the trademark on the web page.

3. The computer program product of claim 1 further comprising:

fifth program instructions to compare a facial template for the graphical, logo portion of the authentic trademark to a corresponding facial portion of the graphical, logo portion of the trademark on the web page to determine a degree of facial match; and

wherein

the fourth program instructions determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match, the degree of text match and the degree of facial match; and

the fifth program instructions are stored on the computer readable storage device(s).

4. The computer program product of claim 1 further comprising:

fifth program instructions to scan the trademark on the web page for a predetermined watermark indicative of a copy of the authentic trademark; and

wherein

the fourth program instructions determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match, the degree of text match and the presence of the predetermined watermark on the trademark on the web page; and

the fifth program instructions are stored on the computer readable storage device(s).

5. The computer program product of claim 1 wherein the third program instructions scale (a) the graphical, logo portion of the trademark on the web page and/or (b) the template, such that both the graphical, logo portion of the trademark on the web page and the template, are substantially a same size, to determine the degree of graphical match.

7. The computer system of claim 5 wherein:

the template is based on a gray scale representation of the graphical, logo portion of the authentic trademark;

the graphical, logo portion of the trademark on the web page is in red-green-blue color; and

the third program instructions convert the graphical, logo portion of the trademark on the web page from red-green-blue color to a gray scale, and compare the template to the gray-scale converted graphical, logo portion of the trademark on the web page.

6. A computer system for determining if a web page includes a trademark that is similar to an authentic trademark, the computer system comprising:

a CPU, a computer readable memory and a computer readable storage device(s);

a web crawler program to identify the web page by progressing through hyperlinks;

first program instructions to identify and recognize, by optical character recognition, characters of a text portion of the trademark on the web page;

second program instructions to compare the recognized characters of the trademark on the web page to corresponding characters of the authentic trademark to determine a degree of text match;

third program instructions to compare a template representing a graphical, logo portion of the authentic trademark to a corresponding graphical, logo portion of the trademark on the web page to determine a degree of graphical match; and

fourth program instructions to determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match and the degree of text match; and

wherein

the first, second, third and fourth program instructions and the web crawler program are stored on the computer readable storage device(s) for execution by the CPU via the computer readable memory.

8. The computer system of claim 6 further comprising:

fifth program instructions to compare a facial template for the graphical, logo portion of the authentic trademark to a corresponding facial portion of the graphical, logo portion of the trademark on the web page to determine a degree of facial match; and

wherein

the fourth program instructions determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match, the degree of text match and the degree of facial match; and

the fifth program instructions are stored on the computer readable storage device(s) for execution by the CPU via the computer readable memory.

9. The computer system of claim 6 further comprising:

fifth program instructions to scan the trademark on the web page for a predetermined watermark indicative of a copy of the authentic trademark; and

wherein

the fourth program instructions determine the similarity of the trademark on the web page to the authentic trademark based on the degree of graphical match, the degree of text match and the presence of the predetermined watermark on the trademark on the web page; and

the fifth program instructions are stored on the computer readable storage device(s) for execution by the CPU via the computer readable memory.

10. The computer system of claim 6 wherein the third program instructions scale (a) the graphical, logo portion of the trademark on the web page and/or (b) the template, such that both the graphical, logo portion of the trademark on the web page and the template, are substantially a same size, to determine the degree of graphical match.

11. A computer program product for determining if a web page includes an object that is similar to a reference object, the object on the web page including text and a graphic, the reference object including reference text and a reference graphic, the computer program product comprising:

a computer readable storage device(s);

a web crawler program to identify the web page by progressing through hyperlinks;

first program instructions to identify and recognize, by optical character recognition, characters of the text of the object on the web page;

second program instructions to compare the recognized characters of the text on the object on the web page to corresponding characters of the reference text of the reference object to determine a degree of text match;

third program instructions to compare a template representing the reference graphic to the graphic of the object on the web page to determine a degree of graphical match; and

fourth program instructions to determine the similarity of the object on the web page to the reference object based on the degree of graphical match and the degree of text match; and

wherein

the first, second, third and fourth program instructions and the web crawler program are stored on the computer readable storage device(s).

12. The computer program product of claim 11 wherein:

the template is based on a gray scale representation of the reference object;

the graphic of the object on the web page is in red-green-blue color; and

the third program instructions convert the graphic of the object on the web page from red-green-blue color to a gray scale, and compare the template to the gray-scale-converted graphic of the object on the web page.

13. The computer program product of claim 11 further comprising:

fifth program instructions to compare a facial template for the reference graphic of the reference object to a facial portion of the graphic of the object on the web page to determine a degree of facial match; and

wherein

the fourth program instructions determine the similarity of the object on the web page to the reference object based on the degree of graphical match, the degree of text match and the degree of facial match; and

the fifth program instructions are stored on the computer readable storage device(s).

14. The computer program product of claim 11 further comprising:

fifth program instructions to scan the object on the web page for a predetermined watermark indicative of a copy of the reference object; and

wherein

the fourth program instructions determine the similarity of the object on the web page to the reference object based on the degree of graphical match, the degree of text match and presence of the predetermined watermark on the object on the web page; and

the fifth program instructions are stored on the computer readable storage device(s).

15. The computer program product of claim 11 wherein the third program instructions scale (a) the graphic of the object on the web page and/or (b) the template, such that both the graphic of the object on the web page and the template are substantially a same size, to determine the degree of graphical match.