Check Image Zone Analysis for Non-Negotiable Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Modern check processing systems face issues with fraudulent or erroneous processing of checks marked as non-negotiable and multiple presentations of single checks, leading to exposure for account holders and financial institutions, as well as invalidity concerns with automatically processed documents like passports and identity documents.

Innovation Solution

Implementing systems and methods that use image processing to identify document types, locate specific text or symbols indicating non-negotiable or exception status, and output rejection indications to prevent further processing, employing OCR and configurable searches for text, images, and pixel patterns across various devices and platforms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated check processing is implemented, then processing efficiency is improved, but fraud detection capability deteriorates

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidfraud detection capability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary analysis of check images by dividing them into zones and searching for non-negotiable indicators before final processing decisions are made. This advance detection prevents fraudulent checks from entering the payment pipeline, maintaining both efficiency and reliability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

An intermediary image processing system is introduced between the check submission and payment processing. This intermediary analyzes the check image for non-negotiable indicators and provides a recommendation, acting as a mediator that enhances fraud detection without significantly impacting processing speed.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If comprehensive zone processing is performed to locate non-negotiable indicators, then detection accuracy is improved, but processing time increases

Engineering Contradiction:

Improvedetection accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The check image is divided into multiple zones, each assigned specific search parameters for non-negotiable indicators. This segmentation allows parallel processing of different areas, improving detection accuracy while managing processing time through efficient resource allocation.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different zones of the check image are processed with different search parameters and attention levels based on their likelihood of containing non-negotiable indicators. High-priority zones receive more thorough analysis, while lower-priority zones use faster processing methods, optimizing the balance between accuracy and speed.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS10679050B2Invalidation recognition and fraud prevention

Publication Date: 2020.06.09 DIGITAL FIRST HOLDINGS LLC

AI summary

Various embodiments herein each include at least one of systems, devices, software, and methods for invalidation recognition and fraud prevention. One embodiment, in the form of a method, includes identifying a document-type of a received image as a check and identifying each of at least one area of the received image as a zone of the check. This method continues by processing each zone to locate text or symbols indicating the check is non-negotiable and subsequently outputting a non-negotiable rejection indication to prevent further payment processing of the check image.