Document Segmentation Using SAD Edge Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing multi-functional devices are inefficient in segmenting and printing multiple documents from a single scanned image, requiring either tedious multiple scans or a two-pass scanning process that increases power consumption and reduces lamp light lifespan.

Innovation Solution

A method and system using a computer-implemented Sum of Absolute Difference (SAD) based edge detection technique to identify potential edge pixels, followed by morphological operations to determine perimeter boundaries and generate image masks, allowing for the segmentation and separate printing of multiple documents from a single input image in a single pass.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multiple documents are captured separately one by one, then each document can be processed individually, but the scanning process becomes tedious and time-consuming

Engineering Contradiction:

Improvescanning efficiencyVSAvoidtime for capturing multiple documents

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent merges multiple document scanning operations into a single scanning pass. The scanner captures all documents placed on the platen simultaneously, creating one composite image that contains multiple documents. This eliminates the need for repeated scanning operations, directly improving productivity while reducing the time loss associated with sequential scanning.

Inventive Principle:

Principle #5Merging (Combining)

2Loss of time

If a single image is captured for multiple documents, then scanning time is reduced, but individual documents cannot be printed separately from the captured image

Engineering Contradiction:

Improvetime for capturing multiple documentsVSAvoidability to print individual documents

Core Design Contradiction:

Loss of timeVSEase of operation

Solution Approach 1:

The patent applies segmentation by dividing the single captured image into multiple individual document images through automated image processing. The system identifies document boundaries, separates overlapping documents, and generates distinct image files for each document. This enables individual documents to be printed separately while maintaining the time efficiency of single-pass scanning.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs self-service by automatically segmenting and processing the captured image without requiring manual intervention. The image processing algorithms autonomously identify document boundaries, separate documents, and create individual output files, making the system self-sufficient in converting a single composite image into multiple printable document images.

Inventive Principle:

Principle #25Self-service

3Ease of operation

If a two-pass scanning process is used to segment and print multiple documents, then individual documents can be printed separately, but power consumption increases and lamp light lifespan reduces

Engineering Contradiction:

Improveability to print individual documentsVSAvoidpower consumption during scanning

Core Design Contradiction:

Ease of operationVSUse of energy by moving object

Solution Approach 1:

The patent combines the segmentation and document separation functions into the first scanning pass. By capturing all documents in a single pass and performing automated image processing to separate them, the system eliminates the need for a second scanning pass. This merging of operations reduces power consumption and extends lamp light lifespan while maintaining the capability to print individual documents separately.

Inventive Principle:

Principle #5Merging (Combining)

4Ease of operation

If a two-pass scanning process is used to segment and print multiple documents, then individual documents can be printed separately, but the lifespan of the lamp light is reduced

Engineering Contradiction:

Improveability to print individual documentsVSAvoidlifespan of lamp light

Core Design Contradiction:

Ease of operationVSDuration of action of stationary object

Solution Approach 1:

The patent merges the segmentation and document separation functions into the first scanning pass. By capturing all documents in a single pass and performing automated image processing to separate them, the system eliminates the need for a second scanning pass. This merging of operations reduces power consumption and extends lamp light lifespan while maintaining the capability to print individual documents separately.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS10169877B2Methods and systems for segmenting multiple documents from a single input image

Publication Date: 2019.01.01 XEROX CORP

AI summary

The present disclosure discloses methods and systems (for example multi-function devices) for segmenting multiple documents from a single input image. The multi-functional device includes a controller unit having a boundary extraction module to process an input image having multiple documents. The processing is performed using a computer implemented sum of absolute difference (SAD) based edge detection technique, to identify potential edge pixels and the region of interest pixels of the plurality of document images. Based on the identified potential edge pixels, perimeter boundaries surrounding each of the plurality of document images are determined. The determined perimeter boundaries and ROI pixels (Image mask for each document) in the input image are then segmented to create separate pages or files for each of the documents present within the input image for the purpose of printing separate files.