Selective Background Removal Using Halftone Saturation Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing background removal techniques in image processing often inadvertently remove highlight areas intended to be preserved, leading to unevenness and failure to remove show-through portions effectively.

Innovation Solution

An image processing apparatus with a first determination unit to identify halftone dot areas and a second unit to assess saturation, allowing for selective background removal by converting pixel values to white based on predetermined levels, distinguishing between achromatic and chromatic areas to preserve highlight details.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If background removal is performed by converting pixel values greater than a predetermined threshold to white, then unnecessary background is removed, but highlight areas that should be preserved are also removed

Engineering Contradiction:

Improvebackground removal accuracyVSAvoidhighlight area preservation

Core Design Contradiction:

Manufacturing precisionVSReliability

Solution Approach 1:

The patent applies different background removal thresholds to different regions of the image based on local characteristics. Halftone dot areas use one threshold while non-halftone areas use another threshold, allowing selective preservation of highlight areas while removing background in appropriate regions

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent changes the pixel value threshold parameter dynamically based on the local image characteristics (halftone dot presence). By adjusting the threshold parameter according to whether a region contains halftone dots, the system achieves both background removal and highlight preservation

Inventive Principle:

Principle #35Parameter changes

2Reliability

If halftone dot portions are preserved by using a fixed density threshold, then halftone dots are not removed, but show-through portions determined to be halftone dots are left as unevenness

Engineering Contradiction:

Improvehalftone dot preservationVSAvoidshow-through removal uniformity

Core Design Contradiction:

ReliabilityVSManufacturing precision

Solution Approach 1:

The patent recognizes that different regions require different treatments: halftone dot areas should preserve highlights while non-halftone areas should remove background uniformly. This local differentiation resolves the contradiction between preserving halftone dots and removing show-through portions

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

Instead of using a single threshold approach, the patent inverts the logic by first identifying halftone dot areas and then applying opposite threshold strategies to halftone versus non-halftone regions, achieving both preservation and uniform removal

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS10194050B2Image processing apparatus, image processing method, and storage medium in which background removal is performed to remove a background included in an input image based on pixel values

Publication Date: 2019.01.29 CANON KK

AI summary

An image processing apparatus includes a first determination unit to determine an attribute of an area included in an input image obtained by reading a document, a second determination unit to determine saturation of an area determined to be a halftone dot area by the first determination unit, and a background removal unit to remove a background included in the input image. The background removal unit converts for an area determined to be a halftone dot area by the first determination unit and whose value indicating saturation is determined to be less than a predetermined value by the second determination unit, a color of a pixel of pixels making up the area, which has a pixel value greater than a first level, into white.