Background OCR during card data entry

Patent metadata

Field	Value
Publication number	US-9324070-B1
Application number	US-201414548152-A
Country	US
Kind code	B1
Filing date	Nov 19, 2014
Priority date	Nov 3, 2014
Publication date	Apr 26, 2016
Grant date	Apr 26, 2016

Abstract

Financial transaction card data can be entered by providing a picture of the card to a server programmed with a text recognition algorithm. The server can perform text recognition on the image at the same time that a consumer enters additional required data, such as a zip code. The server can perform as much text recognition processing as possible in the time the consumer is entering the additional data. Once the additional data is received, a signal can be provided to the server indicating that the user is now waiting for results of the text recognition process, meaning the server should provide them as quickly as possible. Once text recognition results are received, a consumer can make a selection to identify a character which the text recognition algorithm did not sufficiently identify. Based on known account number constraints, the user selection can cause multiple characters to be identified.

First claim

We claim:

1. A method, performed on a mobile computing device, for reducing a number of user corrections entered to obtain a correct account number for a financial transaction card, the method comprising:
sending an image of the financial transaction card from the mobile computing device to a server configured to perform text recognition;
receiving, at the mobile computing device from the server, multiple versions of text recognition results,
wherein each version of the text recognition results comprises multiple character positions with a set of recognized characters for one or more of the character positions corresponding to a proposed account number; and
wherein each version of the text recognition results is associated with a total confidence score;
identifying, as a best guess, a version of the text recognition results that is associated with a highest total confidence score;
selecting, as characters to verify, one or more of the character positions of the best guess that have individual confidence scores below a specified threshold level;
displaying, on a display of the mobile computing device, a first textual representation of the best guess, wherein the first textual representation of the best guess includes one or more input areas, each input area configured to receive, from a user, a character selection for one of the characters to verify;
receiving a user selection, as a selected character for a particular character position, for one of the characters to verify, wherein the user selection is entered using one of the input areas;
identifying a new best guess from the versions of the text recognition results by:
eliminating, from a set of remaining versions of the multiple versions of text recognition results, one or more versions of text recognition results that do not match the selected character;
eliminating, from the set of remaining versions of the multiple versions of text recognition results, one or more versions of text recognition results that either do not satisfy the Luhn algorithm or do not match any of multiple known issuer identification numbers;
updating the total confidence score for each remaining version of the multiple versions of text recognition results; and
selecting, as the new best guess from the remaining versions of the text recognition results, a new version of the text recognition results with a highest total confidence score; and
updating the display of the mobile computing device to show a second textual representation of the new best guess, wherein the second textual representation shows at least:
a first difference from the first the textual representation indicating the selected character in the particular character position, and
a second difference from the first textual representation indicating a defined character in a character position other than the particular character position.

2. The method of claim 1 further comprising:
verifying the proposed account number associated with the new best guess by:
sending the proposed account number associated with the best guess to a financial institution; and
receiving, from the financial institution, a confirmation that the proposed account number associated with the new best guess indicates valid account data.

3. The method of claim 2 further comprising:
sending the verified account number associated with the new best guess to a second server,
wherein the second server is configured to link the financial transaction card to a service provided by a payment service system by storing the proposed account number associated with the new best guess, in a database, with an association to a user and the service provided by the payment service system.

4. The method of claim 2 further comprising:
sending the verified account number associated with the new best guess to a second server, wherein the second server is configured to perform a transaction using the verified account number associated with the new best guess.

5. The method of claim 1 wherein the total confidence score for each selected text recognition result version is based on a combination of individual confidence scores assigned to the recognized characters of that selected text recognition result version.

6. A method for reducing a number of user corrections entered to obtain a correct account number for a financial transaction card, comprising:
receiving, from a server configured to perform text recognition, multiple versions of text recognition results, each version comprising multiple character positions with one or more corresponding recognized characters;
identifying a best guess from the multiple versions of text recognition results;
displaying a textual representation of the best guess;
receiving a correction character corresponding to a character of the textual representation, the correction character indicating a difference between the best guess and the correct account number;
eliminating, based on the correction character, one or more of the multiple versions of text recognition results to create one or more remaining versions by:
eliminating any of the multiple versions that do not match the correction character; and
eliminating any of the multiple versions that, based on the correction character, either do not satisfy the Luhn algorithm or do not match any of multiple known issuer identification numbers;
identifying a new best guess from the remaining versions; and
updating the textual representation with the new best guess showing at least:
a first difference indicating the correction character, and
a second difference indicating a difference between the best guess and the correct account number other than the correction character.

7. The method of claim 6 wherein:
identifying the best guess comprises selecting a version of the text recognition results that is associated with a highest total confidence score; and
identifying the new best guess comprises selecting a version of the text recognition results with an updated highest total confidence score.

8. The method of claim 7 wherein the updated highest total confidence score is based on a combination of individual confidence scores assigned to recognized characters of the new best guess.

9. The method of claim 6 wherein displaying the textual representation of the best guess comprises providing an indication that one or more characters of the textual representation have individual confidence scores below a specified threshold level.

10. The method of claim 6 wherein:
the method is performed on a mobile computing device with a display;
displaying the textual representation of the best guess comprises displaying the textual representation on the display of the mobile computing device with one or more input areas, each indicating a character of the best guess which is a candidate for receiving the correction character; and
the correction character is received through a user selection to one of the input areas.

11. The method of claim 10 wherein:
the characters of the best guess which are candidates for receiving the correction character are selected based on the candidates for receiving the correction character having individual confidence scores below a defined threshold value.

12. The method of claim 10 wherein:
at least one of the input areas for a particular character position is configured to include options for the correction character comprising less than ten different number characters; and
options for the correction character are selected based on a union of the characters in the particular character position from the multiple versions of text recognition results.

13. The method

Assignees

• Square Inc

Inventors

• Bekmann Joachim
• Guo Fei

Classifications

• G06Q20/34 Primary

  using cards, e.g. integrated circuit [IC] cards or magnetic cards · CPC title

• G06Q20/4018

  using the card verification value [CVV] associated with the card · CPC title

• G06Q20/3276

  using a pictured code, e.g. barcode or QR-code, being read by the M-device · CPC title

• G06Q20/3223

  Realising banking transactions through M-devices · CPC title

• G06T7/74

  involving reference images or patches · CPC title