Background Adjustment Component for Scanned Document Image Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing technologies face challenges in effectively suppressing backgrounds, particularly in images with poor contrast between foreground and background, leading to artifacts like 'punch-through' in halftone and highlight regions, due to limitations in processing capabilities and threshold-based segmentation algorithms.

Innovation Solution

The system and method implement a background adjustment component that computes adjusted color values for each pixel based on its background strength and luminance strength, allowing for precise segmentation and classification of background and foreground regions, using advanced processors to minimize artifacts and enable user-selectable background color modifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If threshold-based segmentation algorithms are used for background suppression, then processing speed and throughput are improved, but image quality deteriorates due to punch-through artifacts in halftone and highlight regions

Engineering Contradiction:

Improveprocessing speedVSAvoidimage quality

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The patent segments the image processing task into multiple stages: first identifying background regions using a relaxed threshold, then applying a second more stringent threshold specifically to those identified background regions. This two-stage segmentation approach allows the system to maintain high processing speed while eliminating punch-through artifacts that occur with single-threshold methods.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different thresholding strategies to different regions of the image. Background regions undergo a two-stage thresholding process, while foreground regions are preserved with their original characteristics. This local differentiation ensures high image quality in critical areas without sacrificing overall processing efficiency.

Inventive Principle:

Principle #3Local quality

2Stability of the object's composition

If a high threshold value is used to suppress background, then background uniformity is improved, but foreground regions are adversely impacted causing loss of detail

Engineering Contradiction:

Improvebackground uniformityVSAvoidforeground detail

Core Design Contradiction:

Stability of the object's compositionVSLoss of information

Solution Approach 1:

The patent first segments the image into background and foreground regions using an initial threshold. Then, a second thresholding operation is applied exclusively to the identified background regions. This segmentation approach ensures that foreground regions are never subjected to aggressive thresholding, preserving their detail while achieving background uniformity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different processing treatments are applied to different regions: background regions receive strong thresholding for uniformity, while foreground regions are protected from such processing. This local quality approach ensures that each region receives the appropriate treatment without adversely affecting other regions.

Inventive Principle:

Principle #3Local quality

3Manufacturing precision

If complex background suppression algorithms are used to minimize artifacts, then image quality is improved, but processing complexity and computational load increase

Engineering Contradiction:

Improveimage qualityVSAvoidprocessing complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent divides the complex background suppression task into two simpler sequential operations: first identifying background regions with a relaxed threshold, then applying a second threshold only to those regions. This segmentation of the algorithm reduces computational complexity compared to applying a single complex algorithm to the entire image, while still achieving high image quality.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11508071B2System and method to detect, suppress, and modify background regions of scanned documents

Publication Date: 2022.11.22 XEROX CORP

AI summary

An image processing device includes an input device which receives image adjustment selections from an associated user interface device. Memory of the device stores a user interface generator, which generates a background adjustment selector for presenting to a user on the user interface device; a background adjustment component which, for each of a plurality of pixels of an input image computes adjusted color values, as a function of at least one of: (a) a background adjustment factor computed for the respective pixel, and (b) a background class derived from the computed background adjustment factor, the background adjustment factor being a function of a background strength of the pixel and a luminance strength of the pixel; and an image output component outputs an output image derived from the adjusted color values for the plurality of pixels. A processor implements the background adjustment component and image output component.