Methods and apparatus for nonintrusive monitoring of web browser usage

• US 8,806,006 B2
• Filed: 09/30/2011
• Issued: 08/12/2014
• Est. Priority Date: 04/11/2008
• Status: Active Grant

• Current Assignee: Nielsen & Company Incorporated (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Lee, Morris
• Primary Examiner(s): NGUYEN, MINH CHAU
• Application Number:
  US13/250,623
• Publication Number:
  US 20120023229A1
• Time in Patent Office: 1,047 Days
• Field of Search: 709223-224
• US Class Current: 709/224
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1452 based on positionally close symbols, e.g. amount sign or URL-specific characters
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04N 21/44008 involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/44224 Monitoring of user activity on external systems, e.g. Internet browsing
• CPC Class Codes: H04N 21/4782 Web browsing , e.g. WebTV
• CPC Class Codes: H04N 7/163 by receiver means only

Abstract

An example system disclosed herein comprises a web browser monitor to extract textual information from a captured image comprising at least a portion of content displayed by a web browser implemented by a monitored device, and determine color scheme information for a region of the captured image comprising at least a portion of the content displayed by the web browser. The example system also comprises a central processing facility to process the extracted textual information received from the web browser monitor, and compare the color scheme information received from the web browser monitor to reference color schemes associated with reference web pages to determine web sites accessed using the web browser.

Claims

1. A system to monitor Internet usage, the system comprising:

a web browser monitor to;

extract textual information from a captured image representative of a web page displayed by a web browser implemented by a monitored device; and

determine color scheme information for a region of the captured image comprising at least a portion of the web page displayed by the web browser, the color scheme information for the region of the captured image being represented by a histogram corresponding to respective numbers of pixels in the region having respective different colors displayed in the region; and

a computer processor to compare the color scheme information to reference color schemes associated with respective reference web pages to identify, based on the color scheme information, a web site accessed using the web browser.

2. A system as defined in claim 1 wherein the web browser monitor is to perform optical character recognition to extract first textual information corresponding to at least one of a uniform resource locator (URL) or a title associated with the web page presented by the web browser.

3. A system as defined in claim 1 wherein the web browser monitor is to process the captured image by performing a graphical recognition operation to extract a second region of the captured image characteristic of at least one of an address bar or a title bar of the web browser, and the web browser monitor is to extract the textual information from the extracted second region.

4. A system as defined in claim 1 wherein the web browser monitor is to determine the color scheme information by:

extracting color values of pixels included in the region of the captured image; and

determining the histogram using the color values.

5. A system as defined in claim 1 wherein the web browser monitor is to determine the color scheme information by:

extracting color values of pixels included in the region of the captured image;

discarding ones of the color values associated with one or more colors determined to be non-distinctive; and

determining the histogram using the color values remaining after the discarding of the ones of the color values.

6. A system as defined in claim 1 wherein the web browser monitor is to report the color scheme information and the textual information to the computer processor, and the computer processor is to identify the web site based on the color scheme information and the textual information.

7. A method to monitor web browsing, the method comprising:

extracting textual information from a captured image representative of a web page displayed by a web browser implemented by a monitored device;

determining color scheme information for a region of the captured image comprising at least a portion of the web page displayed by the web browser, the color scheme information for the region of the captured image including a histogram representing respective numbers of pixels in the region having respective different colors displayed in the region; and

comparing, with a processor, the color scheme information to reference color schemes associated with respective reference web pages to identify, based on the color scheme information, a web site accessed using the web browser.

8. A method as defined in claim 7 wherein extracting the textual information further comprises performing optical character recognition to extract first textual information from the captured image corresponding to at least one of a uniform resource locator (URL) or a title associated with the web page presented by the web browser.

9. A method as defined in claim 7 wherein extracting the textual information further comprises:

performing a graphical recognition operation to extract a second region of the captured image that is characteristic of at least one of an address bar or a title bar of the web browser; and

extracting the textual information from the extracted second region.

10. A method as defined in claim 7 further comprising:

extracting color values of pixels included in the region of the captured image; and

determining the histogram using the color values to determine the color scheme information.

11. A method as defined in claim 7 further comprising:

extracting color values of pixels included in the region of the captured image;

discarding ones of the color values respectively associated with corresponding colors determined to be non-distinctive; and

determining the histogram using the color values remaining after the discarding of the ones of the color values.

12. A method as defined in claim 7 further comprising identifying the web site based on the color scheme information and the textual information.

13. A tangible machine readable storage device or storage disk comprising machine readable instructions which, when executed, cause a machine to at least:

extract textual information from a captured image representative of a web page displayed by a web browser implemented by a monitored device;

determine color scheme information for a region of the captured image comprising at least a portion of the web page displayed by the web browser, the color scheme information for the region of the captured image being formatted as a histogram representing respective numbers of pixels in the region having respective different colors displayed in the region; and

compare the color scheme information to reference color schemes associated with respective reference web pages to identify, based on the color scheme information, a web site accessed using the web browser.

14. A tangible machine readable storage device or storage disk as defined in claim 13 wherein to extract the textual information, the machine readable instructions, when executed, further cause the machine to perform optical character recognition to extract first textual information from the captured image corresponding to at least one of a uniform resource locator (URL) or a title associated with the web page presented by the web browser.

15. A tangible machine readable storage device or storage disk as defined in claim 13 wherein to extract the textual information, the machine readable instructions, when executed, further cause the machine to:

perform a graphical recognition operation to extract a second region of the captured image that is characteristic of at least one of an address bar or a title bar of the web browser; and

extract the textual information from the extracted second region.

16. A tangible machine readable storage device or storage disk as defined in claim 13 wherein the machine readable instructions, when executed, further cause the machine to:

extract color values of pixels included in the region of the captured image; and

determine the histogram using the color values to determine the color scheme information.

17. A tangible machine readable storage device or storage disk as defined in claim 13 wherein the machine readable instructions, when executed, further cause the machine to:

extract color values of pixels included in the region of the captured image;

discard ones of the color values respectively associated with corresponding colors determined to be non-distinctive; and

determine the histogram using the color values remaining after the ones of the color values are discarded.

18. A tangible machine readable storage device or storage disk as defined in claim 13 wherein the machine readable instructions, when executed, further cause the machine to identify the web site based on the color scheme information and the textual information.