Distributed Content Identification

• US 20070286454A1
• Filed: 06/05/2007
• Published: 12/13/2007
• Est. Priority Date: 10/16/2001
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Sharma, Ravi, Hannigan, Brett, Brundage, Trent
• Granted Patent: US 7,676,060 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G06T 1/005 Robust watermarking, e.g. average attack or collusion attack resistant
• CPC Class Codes: G06T 2201/0065 Extraction of an embedded watermark; Reliable detection

Abstract

A method of identifying content in a distributed computing system. The method receives an image or audio signal in a first device in the distributed computing system, such as a cell phone or other wireless device. In this device, the method performs an analysis of characteristics of the signal to identify portions of the signal from which to derive a content identifier. The method then sends the portions to a second, remote device in the distributed computing system, such as a server. The server further processes the portions to derive a content identifier, which in turn, is used to look up data corresponding to the content, such as a Uniform Resource Locator. In the case of a wireless telephone network, for example, the method distributes the task of identifying content signals captured through the microphone or camera on the phones in the network.

Claims

1. A method of identifying content in a distributed computing system, the method comprising:

receiving an image or audio signal in a first device in the distributed computing system;

in the first device, analyzing characteristics of the signal to identify portions of the signal from which to derive an identifier; and

sending the portions to a second, remote device in the distributed computing system, wherein the portions are further processed to derive an identifier.

2. The method of claim 1 wherein the analyzing comprises computing signal metrics of the portions and identifying the portions to send to the second device based on the metrics.

3. The method of claim 2 wherein the signal metrics are computed from the signal at selected frequencies.

4. The method of claim 3 wherein the signal metrics comprise signal activity measured at the selected frequencies.

5. The method of claim 1 wherein the analyzing comprises pre-filtering the content signal, and the sending includes sending filtered versions of the portions to the second device.

6. The method of claim 1 wherein the first device comprises a wireless device, and the signal comprises an audio signal received through a microphone of the wireless device.

7. The method of claim 1 wherein the first device comprises a wireless device, and the signal comprises an image signal received through a camera of the wireless device.

8. The method of claim 1 further including:

using the identifier to look up a Uniform Resource Locator associated with the content.

9. A wireless, portable computing device comprising:

a sensor for capturing a content signal;

a processor for processing the content signal to analyze characteristics of the signal to identify portions of the signal from which to derive an identifier; and

a communication module for sending the portions to a second, remote device in the distributed computing system, wherein the portions are further processed to derive an identifier.

10. A server comprising:

a communication link with a remote device for receiving portions of a content signal that have been identified by a remote device by analyzing characteristics of the signal to identify the portions of the signal from which to derive an identifier;

a processor for processing the portions to derive the identifier from the portions;

wherein the derived identifier is used to look up a Uniform Resource Locator associated with the content.