Check Image Boundary Detection via MICR String Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing check reader recognition technologies require the check image to be isolated from the rest of the paper document, making it impossible for companies to use these technologies when scanning entire paper documents intact, as they assume only the check image is present.

Innovation Solution

The method automatically locates the check image within a full page document image by identifying the MICR region and then the top of the check using optical character recognition (OCR) and horizontal raster line detection, allowing the check image to be cropped and used with existing recognition technologies while keeping the original document intact.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing check reader recognition technologies are used, then check recognition accuracy is improved, but the document must be physically processed to separate the check portion, increasing mailroom preparation complexity

Engineering Contradiction:

Improvecheck recognition accuracyVSAvoidmailroom preparation process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical/mailroom preparation process with an automated image processing system. The system uses OCR to detect MICR lines and identify check boundaries digitally, eliminating the need for physical check separation while maintaining recognition accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary detection of the check region within the full document image before recognition processing. By identifying MICR lines and check boundaries in advance, the system prepares the data structure needed for accurate recognition without physical manipulation.

Inventive Principle:

Principle #10Preliminary action

2Stability of the object's composition

If the entire paper document is scanned intact, then document integrity is preserved, but existing check recognition technologies cannot process the image

Engineering Contradiction:

Improvedocument integrityVSAvoidcompatibility with check recognition technology

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system segments the full document image into distinct regions by detecting MICR lines and check boundaries. It identifies the check portion within the larger document while keeping the original document intact, enabling targeted processing of the check region.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary processing layer that bridges full-document scanning and check recognition. It detects check boundaries and extracts check region coordinates, serving as a mediator between the intact document image and the check recognition engine.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automatic check location is implemented, then mailroom preparation is eliminated, but additional image processing steps are required

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidimage processing steps

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically detecting check locations and extracting check regions without human intervention. The automated detection of MICR lines and boundary identification eliminates manual mailroom preparation while maintaining streamlined processing.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8605982B2Check boundary detection by string literal analysis

Publication Date: 2013.12.10 HYLAND SOFTWARE INC

AI summary

A method of locating a check image region within a document image comprising the steps of locating a magnetic ink character recognition region of the check and calculating the top of the check relative to the magnetic ink character recognition region by detection of string literals having a historical and/or contextual relationship to the upper check boundary.