Selective AI Image Color Replacement for Object Distinction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Individuals with color vision deficiencies face difficulties in distinguishing and recognizing color coding in user interfaces and presentations, leading to a need for barrier-free color arrangements that do not cause a strangeness feeling upon color replacement.
Innovation Solution
An automatic image colorization AI model is used to estimate the original color of objects in grayscale images, identify color groups that are hard to distinguish, and replace them with colors that are easily perceived by individuals with color vision deficiencies, while minimizing strangeness feelings by prioritizing color replacements based on confidence levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If color replacement is performed to improve distinguishability for colorblind individuals, then color distinguishability is improved, but strangeness feeling increases and natural perception is affected
Solution Approach 1:
The patent applies local quality by selectively replacing colors only in specific regions where colorblind individuals have difficulty distinguishing objects, rather than uniformly replacing all colors in the image. The system identifies borderline regions between objects and performs targeted color replacement only where needed, preserving natural colors in other areas to avoid strangeness feeling.
Solution Approach 2:
The patent changes color parameters (hue, saturation) of specific color groups that are difficult to distinguish for colorblind individuals, while maintaining other color parameters unchanged. By adjusting only the necessary color attributes in problematic regions and preserving original colors elsewhere, the system improves distinguishability without creating unnatural appearances.
2Measurement precision
If color replacement is performed uniformly across all objects, then color distinguishability is improved, but natural perception of objects is affected
Solution Approach 1:
The system performs color replacement locally only in regions where objects have similar colors and are difficult to distinguish for colorblind individuals. By identifying borderline regions and applying color replacement selectively rather than uniformly across the entire image, the patent preserves natural perception of objects while improving distinguishability where needed.
Solution Approach 2:
The patent applies partial action by performing color replacement only on color groups that meet specific criteria for being difficult to distinguish, rather than applying replacement to all color groups uniformly. This selective approach ensures that natural perception is maintained for objects that do not require color replacement.
3Productivity
If color replacement is performed without selective identification, then processing speed is improved, but color distinguishability improvement is reduced
Solution Approach 1:
The patent segments the image processing task into distinct stages: identifying borderline regions between objects, determining which color groups are difficult to distinguish for colorblind individuals, and selectively replacing colors only in those specific regions. This segmentation allows the system to focus computational resources on problematic areas, maintaining processing efficiency while achieving targeted color distinguishability improvement.
Solution Approach 2:
The system performs preliminary identification of borderline regions and color groups that require replacement before actually performing color replacement. By pre-identifying the specific regions and color groups that need modification, the patent avoids unnecessary processing of unaffected areas, thereby maintaining processing speed while ensuring accurate color distinguishability improvement where needed.
Data Source
AI summary
A computer-implemented method for selectively replacing a color of an object in an original image due to color blindness of a viewer. The method includes identifying whether there are color groups that are hard to be distinguished at a border between one or more objects in an original image. The method further includes generating a grayscale image from the original image and estimating an original color of each pixel in the original image by inputting the generated grayscale image to an automatic colorization artificial intelligence (AI) model. The method further includes determining at least one color group for which color replacement is to be performed and replacing the determined at least one color group with a color that is easily perceived by the person having a color vision deficiency and that is easily distinguished from the other color groups at the border between the identified one or more objects.