Selective Screen Modification for Visually Impaired Users
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current software products that modify screen colors for visually-impaired users indiscriminately affect real-world images, making it difficult to recognize people, animals, and objects in photographs, thereby undermining their effectiveness.
Innovation Solution
A method that selectively modifies the colors or brightness of a computer screen output by analyzing electronic documents to distinguish between real-world images and other content, applying a second modification step to reverse any initial changes made to images, ensuring real-world images are displayed in their original form while modifying text and background as desired.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If color inversion is applied to the entire screen to help visually-impaired users, then text and interface clarity is improved, but real-world images become unrecognizable
Solution Approach 1:
The patent segments the screen content into different types (text, interface elements, and images) and applies color modification selectively. The system identifies photographs through image recognition algorithms and applies inversion only to non-image content, thereby maintaining text clarity while preserving image recognizability.
Solution Approach 2:
The patent applies different quality treatments to different regions of the screen. Text and interface elements receive full color inversion for maximum readability, while photograph regions receive no inversion to maintain their natural appearance and recognizability. This local differentiation resolves the contradiction between overall clarity and specific image preservation.
2Object-affected harmful factors
If color modification is applied uniformly across the screen, then visual strain is reduced for visually-impaired users, but the natural appearance of photographs is lost
Solution Approach 1:
The system segments screen content into modifiable regions (text, background) and protected regions (photographs). By applying color modification only to the segmented text and background areas, the system reduces eye strain for visually-impaired users while preserving the stable, original appearance of photographs.
Solution Approach 2:
The patent introduces an intermediary image recognition layer that sits between the display content and the color modification process. This intermediary identifies photographs and prevents modification from being applied to them, acting as a mediator that protects image integrity while allowing modification elsewhere to reduce eye strain.
3Ease of operation
If the entire screen output is modified for accessibility, then interface usability is improved, but photographic content becomes distorted
Solution Approach 1:
The patent divides the display output into operable interface elements and photographic content. Color modification is applied to interface elements (buttons, text, menus) to improve usability for visually-impaired users, while photographs are segmented out and excluded from modification to maintain their fidelity and accuracy.
Solution Approach 2:
Different quality standards are applied locally across the screen: interface elements receive aggressive color modification for maximum accessibility, while photographs maintain their original quality and colors. This local quality differentiation resolves the contradiction between overall interface usability and specific image fidelity.
Data Source
AI summary
A method of selectively modifying output of a computer screen. An application hosts an electronic document having a background, alphanumerical characters, and one or more images. A modification tool performs a first modification step in which the modification tool modifies color and/or brightness of all content displayed on the computer screen. The invention identifies and analyzes images within that content to determine whether each image is a real-world image, such as a photograph. A second modification step, which is opposite to the first modification step, is applied to each real-world image, thereby reversing initial modification and returning the image to original, unmodified form. The computer screen outputs the modified electronic document having a modified background and modified text, but outputs the real-world image in its original, unmodified form.