OCR Image Segmentation for Automated Account Data Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current OCR systems are inefficient and inaccurate in automatically processing and evaluating contextual and identification information from images, leading to increased processing time and costs, particularly in tasks like processing returned mail.

Innovation Solution

An OCR-based system utilizing enhanced image processing techniques, including image segmentation and machine learning, to optimize image quality, classify image types, and automatically execute actions associated with online accounts by linking extracted metadata to account information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional OCR processing is used, then the system is simple to implement, but the processing accuracy and completeness are insufficient

Engineering Contradiction:
Improveprocessing accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the image processing into distinct segments: image capture, image optimization, segmentation, OCR processing, and action execution. Each segment handles a specific task independently, improving overall accuracy while managing complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary image optimization and segmentation before OCR processing. By preparing the image in advance (correcting skew, adjusting contrast, segmenting regions), the subsequent OCR processing achieves higher accuracy without requiring a completely complex system.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If manual processing is used, then the system complexity is low, but the processing time and costs increase

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidautomation system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system automatically executes actions based on extracted information without requiring manual intervention. The automated workflow includes image capture, processing, information extraction, and direct execution of actions such as updating account information or triggering notifications, eliminating manual processing steps.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processing with automated computer-based processing. Manual evaluation of image information is substituted with automated OCR processing, machine learning classification, and programmatic action execution, significantly improving productivity.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If comprehensive image processing is applied, then the processing accuracy improves, but the processing time increases

Engineering Contradiction:
Improveevaluation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies different processing qualities to different regions of the image. Through segmentation, it identifies specific regions containing critical information (such as address fields or account numbers) and applies enhanced processing only to those regions rather than uniformly processing the entire image, reducing overall processing time while maintaining high accuracy for critical data.

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS12183102B2Enhanced optical character recognition (OCR) image segmentation system and method
Publication Date: 2024.12.31 CAPITAL ONE SERVICES LLC
  • US12183102B2 patent drawing
  • US12183102B2 patent drawing
  • US12183102B2 patent drawing

AI summary

Optical character recognition (OCR) based systems and methods for extracting and automatically evaluating contextual and identification information and associated metadata from an image utilizing enhanced image processing techniques and image segmentation. A unique, comprehensive integration with an account provider system and other third party systems may be utilized to automate the execution of an action associated with an online account. The system may evaluate text extracted from a captured image utilizing machine learning processing to classify an image type for the captured image, and select an optical character recognition model based on the classified image type. They system may compare a data value extracted from the recognized text for a particular data type with an associated online account data value for the particular data type to evaluate whether to automatically execute an action associated with the online account linked to the image based on the data value comparison.