Receipt Image Splitting Module for Batch Expense Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing expense report systems face inefficiencies when processing multiple receipts, as they often require capturing each receipt individually, leading to time-consuming and error-prone processes, and fail to correctly process multiple receipts scanned at once.

Innovation Solution

Implementing an image splitting module and OCR engine within the system, which allows for the capture and processing of multiple receipts simultaneously by splitting image data and using templates to accurately extract data from receipt images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple receipts are captured in a single scan, then processing time is reduced, but the system incorrectly processes the capture data by treating multiple receipts as a single receipt

Engineering Contradiction:

Improvereceipt processing throughputVSAvoiddata processing accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies segmentation by dividing the captured image data into multiple separate receipt images using an image splitting module. This module identifies boundaries between adjacent receipts and separates them into individual image files, allowing each receipt to be processed independently and accurately by the existing OCR system while maintaining the efficiency benefit of batch scanning.

Inventive Principle:

Principle #1Segmentation

2Reliability

If receipts are captured one at a time, then data processing accuracy is maintained, but the process becomes time consuming and error prone

Engineering Contradiction:

Improvedata capture accuracyVSAvoidreceipt capture time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by performing image splitting and receipt separation before the main data processing step. The system pre-processes the batch-captured image to identify and separate individual receipts, creating ready-to-process individual receipt files that can then be handled by the existing accurate but slower processing pipeline.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If the scanning surface is enlarged to accommodate multiple receipts, then capture efficiency increases, but the complexity of processing and correctly identifying individual receipts increases

Engineering Contradiction:

Improvebatch capture capabilityVSAvoidimage processing complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces an image splitting module as an intermediary component between the batch image capture device and the OCR processing system. This intermediary module handles the complexity of identifying boundaries, separating receipts, and creating individual image files, shielding the rest of the system from this complexity while enabling batch processing capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9245296B2Expense report system with receipt image processing

Publication Date: 2016.01.26 RICOH CO LTD

AI summary

A system and method for processing receipt image data is disclosed. The system includes an image capture device and an image splitting module. In one embodiment, the image capture device is augmented to capture in a single scan four images arranged in a 2×2 grid pattern, nine images arranged in a 3×3 grid pattern, twelve images arranged in a 3×4 grid pattern or sixteen images arranged in a 4×4 grid pattern. The image splitting module recognizes scans of the image capture device that include multiple images and splits the images for the proper processing by the rest of the system.