IP Library Granted Patent US 12,437,567
Granted Patent B2
US 12,437,567 · App. 17/754,198 · Granted Oct 7, 2025

Computer-implemented method for optical character recognition

Inventors: Daniel Albertini (Vienna, AT); David Dengg (Vienna, AT); Martin Cerman (Vienna, AT); Peter Sperl (Vienna, AT); Hannes Duchkowitsch (Vienna, AT)
Assignee: ANYLINE GmbH
G06V30/10G06V10/82G06V30/1916
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 12,437,567
App. No.
17/754,198
Granted
Oct 7, 2025
Kind
B2
Abstract

A computer-implemented method for optical character recognition and corresponding data processing apparatus, computer program and computer-readable medium. The method includes the following: receiving image data of an input image having one or more characters and applying one or more data processing operations to the received image data, wherein at least one of the data processing operations is configured to return the one or more characters of the input image, wherein each data processing operation is selected from a predefined set of available data processing functions according to a processing configuration, wherein the available data processing functions are precompiled functions, and wherein the processing configuration can be changed at runtime.

Claims (35)

1. A computer-implemented method for optical character recognition, the method comprising:

receiving image data of an input image having one or more characters;

applying two or more different data processing operations to the received image data,

wherein at least one of the two or more different data processing operations is configured to return the one or more characters of the input image,

wherein each data processing operation is selected from a predefined set of available data processing functions according to a processing configuration,

wherein the available data processing functions are precompiled functions; and

before applying the two or more different data processing operations, loading the processing configuration and a network configuration from a remote service at runtime,

wherein the processing configuration determines a sequence of the two or more different data processing operations, and

wherein at least one of the two or more different data processing operations includes propagating data through one or more artificial neural networks configured by the loaded network configuration.

2. The method according to claim 1 , wherein the processing configuration further determines at least one of: a total number of data processing operations or a parametrization of the two or more different data processing operations.

3. The method according to claim 1 , further comprising:

validating the processing configuration received from the remote service before applying the two or more different data processing operations.

4. The method according to claim 1 , further comprising:

determining that the processing configuration received from the remote service is invalid and loading a previously cached processing configuration.

5. The method according to claim 1 , further comprising:

requesting from the remote service a specific processing configuration associated with at least one of: an application identifier or a hardware identifier of a device running the method.

6. The method according to claim 1 , wherein the loading the processing configuration from a remote service includes:

receiving an encrypted processing configuration from the remote service; and

decrypting the encrypted processing configuration received from the remote service using a secret key.

7. The method according to claim 1 , further comprising:

before applying the two or more different data processing operations, authenticating the process configuration.

8. The method according to claim 1 , wherein the receiving image data of an input image includes capturing one or more images with an image sensor.

9. The method according to claim 8 , wherein the steps of receiving image data and applying the two or more different data processing operations are:

repeated for a sequence of input images; and

run in parallel or alternate.

10. A data processing apparatus comprising a processor for carrying out the method of claim 1 .

11. A non-transitory computer-readable medium having instructions for a processor stored thereon such that, when the processor executes the instructions, the processor performs operations for optical character recognition comprising:

receiving image data of an input image having one or more characters;

applying two or more different data processing operations to the received image data,

wherein at least one of the two or more different data processing operations is configured to return the one or more characters of the input image,

wherein each data processing operation is selected from a predefined set of available data processing functions according to a processing configuration,

wherein the available data processing functions are precompiled functions; and

before applying the two or more different data processing operations, loading the processing configuration and a network configuration from a remote service at runtime,

wherein the processing configuration determines a sequence of the two or more different data processing operations, and

wherein at least one of the two or more different data processing operations includes propagating data through one or more artificial neural networks configured by the loaded network configuration.

Assignments (2)
SECURITY INTEREST Recorded Jul 13, 2023
From: ANYLINE GMBH
To: ATEMPO GROWTH I
Reel/Frame 064565/0233 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 7, 2022
From: ALBERTINI, DANIEL; DENGG, DAVID; CERMAN, MARTIN; SPERL, PETER; DUCHKOWITSCH, HANNES
To: ANYLINE GMBH
Reel/Frame 060117/0262 →
Priority Claims (1)
EP 19200582 · Sep 30, 2019 · regional
Continuity (1)
Related Publication 20220327849A1 · Oct 13, 2022
References Cited (25)
US 6301381B1 · Hayashi · 2001 [cited by examiner]
US 10007863B1 · Pereira · 2018 [cited by examiner]
US 10621727B1 · Becker · 2020 [cited by examiner]
US 20130219307A1 · Raber et al. · 2013 [cited by applicant]
US 20170177968A1 · Albertini · 2017 [cited by applicant]
US 20180033147A1 · Becker · 2018 [cited by examiner]
US 20190073571A1 · Kalyuzhny · 2019 [cited by examiner]
US 20190073681A1 · Chen · 2019 [cited by applicant]
US 20190080164A1 · Duke · 2019 [cited by examiner]
US 20190236445A1 · Das · 2019 [cited by examiner]
US 20190392196A1 · Sagonas · 2019 [cited by examiner]
US 20200202173A1 · Oishi · 2020 [cited by examiner]
CN 109087236A · 2018 [cited by applicant]
JP 2002342739 · 2002 [cited by applicant]
JP 2003122442 · 2003 [cited by applicant]
JP 2019505149 · 2019 [cited by applicant]
Hand Written Character Recognition Using Back Propagation Network, Srinivasa Kumar Devireddy et al., 2009, pp. 257-269 (Year: 2009). [cited by examiner]
Optical Character Recognition by a Neural Network, Michael Sabourin et al., 1992, pp. 843-852 (Year: 1992). [cited by examiner]
Optical Character Recognition using Back Propagation Neural Network, Shyla Afroge et al., 2016, IEEE, pp. 1-4 (Year: 2016). [cited by examiner]
Notice of Reasons for Rejection (Office Action) dated Apr. 25, 2023 for Japanese Patent Appl. No. 2022-519974. [cited by applicant]
Sabourin, Michael , et al.; “Optical Character Recognition by a Neural Network”; Neural Networks, vol. 5, Issue 5; Elsevier Science Direct; Pergamon Press Ltd.; Sep. 1, 1992; 10 Pages. [cited by applicant]
Chattopadhyay, Tanushyam, et al.; “Automatic Selection of Binarization Method for Robust OCR”; 2013 12th International Conference on Document Analysis and Recognition; IEEE; Washington, DC, USA; Aug. 25, 2013; 5 Pages. [cited by applicant]
Beale, Mark Hudson, et al.; “Neural Network Toolbox (TM), User's Guide”; Matlab (R), MathWorks; Natick, MA.; Feb. 2, 2015; 2 Pages. [cited by applicant]
Extended European Search Report; Application No. 19200582.5; Completed: Apr. 2, 2020; Issued: Apr. 14, 2020; 22 pages. [cited by applicant]
International Search Report and Written Opinion of the International Searching Authority; PCT/EP2020/077362; Completed: Oct. 22, 2020; Mailing Date: Oct. 30, 2020; 15 Pages. [cited by applicant]