Mobile Financial Document Image Processing via Server Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing mobile device-based financial document processing systems face challenges in efficiently extracting data due to limited processing power, large image file sizes, and difficulties in separating foreground from background in images with complex backgrounds or weak image foregrounds, leading to background noise and inaccurate orientation and size corrections.

Innovation Solution

A system that captures color images on a mobile device, converts them to grayscale or color-reduced images, and transmits these to a server for geometric correction, binarization, orientation adjustment, and size normalization using MICR lines, ensuring accurate document processing without distorting MICR characters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple image processing steps are performed on a mobile device, then data extraction capability is improved, but processing time increases and user productivity decreases

Engineering Contradiction:

Improvedata extraction accuracyVSAvoiduser productivity

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent divides the image processing workflow into two segments: mobile device (capture and transmit) and server (processing and enhancement). This segmentation allows complex processing to occur on the server while the mobile device maintains high productivity, resolving the contradiction between data extraction accuracy and user productivity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a server as an intermediary between the mobile device and the data extraction process. The server handles computationally intensive image processing tasks, enabling accurate data extraction without burdening the mobile device's processing capabilities, thus maintaining user productivity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If large color images are transmitted to a server, then image quality is improved, but communication bandwidth consumption increases and transmission time increases

Engineering Contradiction:

Improveimage qualityVSAvoidcommunication bandwidth

Core Design Contradiction:

Measurement precisionVSLoss of energy

Solution Approach 1:

The patent changes the parameter of image data from full-color high-resolution to grayscale or color-reduced format before transmission. This parameter change maintains sufficient image quality for data extraction while significantly reducing the data size, thereby conserving communication bandwidth and reducing transmission time.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If a single threshold algorithm is applied to the entire document, then processing speed is improved, but background noise increases and measurement precision decreases

Engineering Contradiction:

Improveprocessing speedVSAvoidforeground-background separation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies different thresholding strategies to different regions of the document. Instead of a uniform single threshold, the system uses adaptive thresholding that adjusts to local characteristics, improving foreground-background separation accuracy in complex regions while maintaining reasonable processing speed.

Inventive Principle:

Principle #3Local quality

4Extent of automation

If MICR confidence comparison is used to correct orientation, then automation is improved, but processing speed decreases due to multi-threading limitations

Engineering Contradiction:

Improveorientation correction automationVSAvoidprocessing speed

Core Design Contradiction:

Extent of automationVSProductivity

Solution Approach 1:

The patent performs preliminary geometric correction and binarization before orientation correction. By preparing the image in advance with these operations, the subsequent MICR confidence-based orientation correction can proceed more efficiently, reducing the overall processing time while maintaining automation.

Inventive Principle:

Principle #10Preliminary action

5Measurement precision

If geometric correction is applied to correct image size, then measurement precision is improved, but MICR character distortion occurs

Engineering Contradiction:

Improveimage size accuracyVSAvoidMICR character shape accuracy

Core Design Contradiction:

Measurement precisionVSManufacturing precision

Solution Approach 1:

The patent employs dynamic scaling that adapts to the specific document type and MICR line characteristics. By adjusting the scaling parameters dynamically based on detected features, the system achieves accurate size correction while preserving MICR character integrity through intelligent parameter adjustment.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS8995012B2System for mobile image capture and processing of financial documents

Publication Date: 2015.03.31 RDM CORP

AI summary

An automated document processing system, particularly for mobile image capture and processing of financial documents to enhance images captured on a mobile device with camera capabilities for data extraction. The systems comprise a mobile device that includes a capture device configured to capture color images of documents, and that has a processor for performing certain operations, such as color reduction, and a transmitter for sending an image from the mobile device to a server. The server is configured to optimize and enhance the image, and to apply an improved binarization algorithm using a window within a relevant document field and/or a threshold for the document field. Orientation correction may also be performed at the server by reading the MICR line on a check and comparing a MICR confidence to a threshold. A check image may also be size corrected using features of the MICR line and expected document dimensions.