# US 2014/0369590 A1 · Media authentication

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0369590 A1
- Document ID: US20140369590A1
- Status: Published application
- Kind: A1
- Application number: 13/919,064
- Filed: 2013-06-17
- Published: 2014-12-18
- Earliest claimed: 2013-06-17
- Assignees: NCR Corporation
- Applicants: Ncr Corporation
- Inventors: Chao He; Gary Ross
- Web page: https://patentgrep.com/patent/US20140369590A1

## CPC

- G07D 7/202: using pattern matching
- G06V 30/2253: {Recognition of characters printed with magnetic ink (G06V30/2247 takes precedence)}
- G07D 7/04: Testing magnetic properties of the materials thereof, e.g. by detection of magnetic imprint (G07D7/01 takes precedence)
- G07D 7/12: Visible light, infrared or ultraviolet radiation
- G07D 7/162: Length or width
- G07D 7/00: Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D: HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method of authenticating a media item is described. The method comprises: measuring a magnetic signal along the media item, converting the measured signal to a calibrated length signal, aligning the calibrated length signal with a reference signal, extracting features from the aligned signal, and classifying the media item based on the extracted features.

## Claims

### Claim 1

A method of authenticating a media item, the method comprising:
measuring a magnetic signal along the media item,
converting the measured signal to a calibrated length signal,
aligning the calibrated length signal with a reference signal,
extracting features from the aligned signal, and
classifying the media item based on the extracted features.

### Claim 2 (depends on 1)

A method according to claim 1, wherein the step of measuring a magnetic signal along the media item comprises measuring a plurality of magnetic signals along the media item.

### Claim 3 (depends on 1)

A method according to claim 1, wherein the method comprises the further step, after measuring the signal, of removing system noise from the measured signal.

### Claim 4 (depends on 1)

A method according to claim 1, wherein the method comprises the further step, after measuring the signal, of averaging a plurality of sampled points to create one averaged sample point.

### Claim 5 (depends on 1)

A method according to claim 1, wherein the method comprises the further step of converting the measured signal to a calibrated length signal.

### Claim 6 (depends on 5)

A method according to claim 5, wherein converting the measured signal to a calibrated length signal comprises ascertaining a center point of the measured signal length and cropping the measured signal length to half of the desired length in opposite directions from the center point.

### Claim 7 (depends on 1)

A method according to claim 1, wherein the method comprises the further step of normalizing the magnetic signal.

### Claim 8 (depends on 1)

A method according to claim 1, wherein the step of extracting features from the aligned signal comprises the further steps of (i) extracting features from the spatial domain, and (ii) extracting features from the frequency domain.

### Claim 9 (depends on 1)

A method according to claim 1, wherein the step of classifying the media item based on the extracted features comprises a positive test and a negative test.

### Claim 10 (depends on 9)

A method according to claim 9, wherein the positive test comprises validating that the aligned signal from the media item has a magnetic response at the spatial locations corresponding to magnetic ink printed features of a genuine media item.

### Claim 11 (depends on 9)

A method according to claim 9, wherein the negative test comprises validating that the aligned signal from the media item has no magnetic response at the spatial locations that are not printed by magnetic inks in a genuine media item.

### Claim 12 (depends on 11)

A method according to claim 11, wherein the negative test comprises the further steps of (i) ascertaining start and end coordinates of each area of the media item that should not have a magnetic response by accessing data stored in a reference, (ii) calculating, for each magnetic-free zone, a ratio of non-zero points to all points along the length of the magnetic-free zone, and (iii) calculating an overall average of the ratios for all magnetic-free zones, and (iv) comparing the overall average to a threshold specified by a reference.

### Claim 13 (depends on 9)

A method according to claim 9, wherein the step of classifying the media item based on the extracted features further comprises combining the results of the positive test and the negative test.

### Claim 14 (depends on 1)

A method according to claim 1, wherein the step of classifying the media item based on the extracted features includes the sub-step of classifying the media item based on a combination of image-based processing and the extracted features relating to the magnetic response.

### Claim 15

A self-service terminal comprising a magnetic reader for measuring magnetic signals from a media item, and a controller operable to: (i) convert the measured signal to a calibrated length signal, (ii) align the calibrated length signal with a reference, (iii) extract features from the aligned signal, and (iv) classify the media item based on the extracted features.

### Claim 16

A method of creating a template for use in media validation, the method comprising:
receiving magnetic signals retrieved from a plurality of channels, each channel including magnetic information from part of a media item;
collating magnetic signals for a plurality of media items;
creating a reference signal for each channel by combining signals from different media items for the same channel;
deriving at least one feature for each channel;
calculating a positive test parameter;
calculating a negative test parameter; and
creating a template including the reference signals, the derived features, the positive test parameter, and the negative test parameter.

### Claim 17 (depends on 16)

A method according to claim 16, wherein the method includes the further step of identifying channels that include no meaningful magnetic information, and discarding those channels so that only valid channels are stored in the template.

### Claim 18 (depends on 16)

A method according to claim 16, wherein the method include the further step of aligning signals from each valid channel with the reference signal for that channel.

### Claim 19

A method of authenticating a media item using magnetic information, the method comprising:
measuring a magnetic signal along the media item,
extracting features from the magnetic signal, and
classifying the media item based on the extracted features by using a positive test and a negative test.

### Claim 20 (depends on 19)

A method according to claim 19, wherein the negative test is based on a magnetic free zone.
