Image content based advertisement system

Patent metadata

Field	Value
Publication number	US-10043193-B2
Application number	US-69030910-A
Country	US
Kind code	B2
Filing date	Jan 20, 2010
Priority date	Jan 20, 2010
Publication date	Aug 7, 2018
Grant date	Aug 7, 2018

Abstract

A system for serving an advertisement in a networked environment receives data that defines a user selection of an image. The system also selects an advertisement associated with the user selection and communicates the selected advertisement to the user. The data that defines the user selection includes an x selection coordinate, a y selection coordinate, a width, and a height that defines a region of an image. The user selection defines also defines a scene of a video. The system also includes circuitry and logic configured to extract text and to detect objects from an image region defined by the user selection and to select an advertisement associated with any extracted text and/or detected object.

First claim

We claim:

1. A method for serving an advertisement in a networked system, the method comprising:
receiving, by an image processing server and from a web browser running on a user device, user selection data describing a user selection on an image displayed by the web browser, object data identifying an object associated with the user selection, and scripting information configured to indicate coordinates of the user selection, wherein the object includes textual information;
adaptively determining, by the image processing server, an image region that includes at least a portion of the image based on the coordinates of the user selection and all characters in a particular set of text included in the object, wherein a dimension of the image region is automatically adapted to capture all the characters in the particular set of text detected from the object;
extracting, by the image processing server, the image region from the image according to an identification of pixels that define the image region;
determining, by the image processing server, textual content within the image region based on the characters in the particular set of text;
selecting, by the image processing server, an advertisement associated with the determined textual content within the image region; and
controlling, by the image processing server, transmission of an advertisement tag embedded into the image to the web browser such that reading the advertisement tag causes the web browser to retrieve the advertisement and display the advertisement in a region adjacent to the image displayed by the web browser.

2. The method according to claim 1 , wherein the user selection data, the object data, and the scripting information are received based on a pointer or a cursor moving over or near the object.

3. The method according to claim 1 , wherein the user selection data, the object data, and the scripting information are received based on display of the object.

4. The method according to claim 1 , wherein the user selection data and the object data defines, at least in part, a scene of a video including the object, and wherein the method further comprises selecting the advertisement according to the scene of the video.

5. The method according to claim 1 , wherein selecting the advertisement comprises selecting the advertisement based on the textual content within the image region.

6. The method according to claim 1 , wherein selecting the advertisement comprises selecting the advertisement based on object information extracted from the object.

7. The method according to claim 1 , wherein the image includes data configured to cause a browser to indicate to the user the object is associated with the advertisement.

8. A method for serving an advertisement in a networked system, the method comprising:
receiving, by an image processing server, a request to display a requested image, from a user;
determining, by the image processing server, whether to embed an advertisement into the requested image by a script run by the image processing server, the script configured to use scripting information embedded in the requested image, the scripting information configured to indicate coordinates of a user selection on the requested image;
adaptively determining, by the image processing server, an image region that includes at least a portion of the requested image based on the coordinates of the user selection, wherein a dimension of the image region is automatically adapted to capture characters in a particular set of text detected from an object corresponding to the user selection;
extracting, by the image processing server, the image region from the requested image according to an identification of pixels that define the image region;
determining, by the image processing server, textual content within the image region based on the characters in the particular set of text;
selecting, by the image processing server, an advertisement associated with the determined textual content within the image region;
embedding, by the script, an advertisement tag into the requested image; and
transmitting, by the image processing server, the advertisement tag to a web browser such that reading the advertisement tag causes the web browser to retrieve the advertisement and display the advertisement in a region adjacent to the requested image.

9. The method according to claim 8 , wherein the request includes the scripting information, and the scripting information includes data that defines a user selection box that includes an x selection coordinate, a y selection coordinate, a width of the box, and a height of the box.

10. A system for serving an advertisement in a networked system comprising:
an image processing server configured to:
receive data that includes a user selection on an image and data associated with a box that encompasses the user selection, and wherein the data associated with the box includes scripting information embedded into the image and configured to indicate coordinates of the box;
adaptively determine an image region that includes at least a portion of the image based on coordinates of the user selection and the data associated with the box, wherein a dimension of the image region is automatically adapted to capture all characters in a particular set of text detected from an object located within the box;
extract the image region from the image according to an identification of pixels that define the image region;
determine textual content within the image region based on the characters in the particular set of text;
select, according to at least the scripting information, an advertisement associated with the determined textual content within the image region; and control transmission of an advertisement tag embedded into the image to a web browser displaying the image such that reading the advertisement tag causes the web browser to retrieve the advertisement and display the advertisement in a region adjacent to the image displayed by the web browser.

11. The system according to claim 10 , wherein the scripting information includes an x selection coordinate of the box, and a y selection coordinate of the box.

12. The system according to claim 10 , wherein the data defines a scene of a video, and wherein the system further comprises circuitry configured to select the advertisement according to the scene of a video.

13. The system according to claim 10 , wherein the image processing server further comprises circuitry configured to extract object information corresponding to the object from the user selection and to select the advertisement according to the object information.

14. The system according to claim 10 , wherein the image processing server further comprises circuitry configured to select the advertisement according to the scripting information.

15. Circuitry configured to:
receive data that includes a user selection on an image, wherein the data identifies an object associated with the user selection and includes scripting information configured to indicate coordinates of the user selection, wherein the object includes textual information;
adaptively determine an image region that includes at least a portion of the image based on the coordinates of the user selection and the textual information included in the object, wherein a dimension of the image region is automatically adapted to capture all characters in a particular set of text detected from the object;
extract the image region from the image according to an identification of pixels that define the image region;
determine textual content within the image region based on the c

Assignees

• Watfa Allie K
• Nussel Dale
• Kilroy Jonathan
• Excalibur Ip Llc

Inventors

• Watfa Allie K
• Nussel Dale
• Kilroy Jonathan

Classifications

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title

• G06Q30/0255

  based on user history · CPC title