IP Library Granted Patent US 9,208,378
Granted Patent B2
US 9,208,378 · App. 13/629,755 · Granted Dec 8, 2015

Methods of processing data from multiple image sources to provide normalized confidence levels for use in improving performance of a recognition processor

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,208,378
App. No.
13/629,755
Granted
Dec 8, 2015
Kind
B2
Abstract

A method comprises receiving from a first data source first recognition results which are associated with the first data source, and receiving from a second data source second recognition results which are associated with the second data source. The method further comprises processing a first set of confidence levels associated with the first recognition results to provide a first set of normalized confidence levels associated with the first data source, and processing a second set of confidence levels associated with the second recognition results to provide a second set of normalized confidence levels associated with the second data source. The method also comprises storing the first set of normalized confidence levels associated with the first data source in a first table of normalized confidence levels and the second set of normalized confidence levels associated with the second data source in a second table of normalized confidence levels.

Claims (14)

1. A method of operating a recognition workstation of an image-based check processing system, the method comprising:

receiving from a first remote deposit capture device first check image data which is representative of a first image of a check;

receiving from a second remote deposit capture device second check image data which is representative of a second image of the check;

electronically by a recognition processor, processing the first check image data to obtain a number of confidence levels associated with the first check image data;

electronically by a recognition processor, processing the second check image data to obtain a number of confidence levels associated with the second check image data;

electronically by a recognition processor, processing the confidence levels associated with the first check image data to provide a first set of normalized confidence levels associated with the first check image data, and wherein processing further includes calculating each normalized confidence level for the first set by dividing a total count of successful first check image reads at a given confidence level or higher confidence level than the given confidence level by a total count of first check image reads at the given confidence level or the higher confidence level;

electronically by a recognition processor, processing the confidence levels associated with the second check image data to provide a second set of normalized confidence levels associated with the second check image data, and wherein processing further includes calculating each normalized confidence level for the second set by dividing a total count of successful second check image reads at a given confidence level or higher confidence level than the given confidence level by a total count of second check image reads at the given confidence level or the higher confidence level; and

electronically by a recognition processor, storing each of the first and second sets of normalized confidence values in a respective table to allow normalized confidence levels from one table to be compared with normalized confidence levels from the other table.

2. A method according to claim 1 , further comprising:

electronically by a recognition processor, comparing normalized confidence levels from one table with normalized confidence levels from the other table.

3. A method according to claim 2 , further comprising:

electronically by a recognition processor, selecting one of the first and second check image data based upon comparison of the normalized confidence levels from one table with normalized confidence levels from the other table.

4. A method according to claim 2 , wherein the first remote deposit capture device and the second remote deposit capture device comprise the same device.

5. A method according to claim 1 , wherein the method is performed by a computer having a memory executing one or more programs of instructions which are tangibly embodied in a program storage medium readable by the computer.

Assignments (8)
RELEASE OF SECURITY INTEREST Recorded Sep 30, 2024
From: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
To: NCR VOYIX CORPORATION (F/K/A NCR CORPORATION)
Reel/Frame 069037/0952 →
SECURITY INTEREST Recorded Sep 30, 2024
From: DIGITAL FIRST HOLDINGS LLC
To: UBS AG, STAMFORD BRANCH, AS COLLATERAL AGENT
Reel/Frame 069083/0202 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: NCR VOYIX CORPORATION
To: DIGITAL FIRST HOLDINGS LLC
Reel/Frame 069040/0094 →
CHANGE OF NAME Recorded Dec 7, 2023
From: NCR CORPORATION
To: NCR VOYIX CORPORATION
Reel/Frame 065820/0704 →
SECURITY INTEREST Recorded Oct 25, 2023
From: NCR VOYIX CORPORATION
To: BANK OF AMERICA, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 065346/0168 →
RELEASE OF PATENT SECURITY INTEREST Recorded Oct 25, 2023
From: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
To: NCR VOYIX CORPORATION
Reel/Frame 065346/0531 →
SECURITY AGREEMENT Recorded Apr 18, 2016
From: NCR CORPORATION; NCR INTERNATIONAL, INC.
To: JPMORGAN CHASE BANK, N.A.
Reel/Frame 038646/0001 →
SECURITY AGREEMENT Recorded Jan 15, 2014
From: NCR CORPORATION; NCR INTERNATIONAL, INC.
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 032034/0010 →