Screen Reader Image Descriptions With Adaptive Verbosity

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Screen readers often generate inefficient and resource-intensive descriptions of images, leading to degraded user experience and excessive power consumption for visually impaired users.

Innovation Solution

A system that receives a verbosity setting, identifies image foreground and background, ranks objects within the foreground, and selectively generates descriptions based on this setting to conserve processing resources and power.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If screen readers generate comprehensive descriptions of images, then information completeness is improved, but power consumption and processing resources increase

Engineering Contradiction:

Improveinformation completenessVSAvoidpower consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the level of detail in image descriptions based on user preferences and contextual factors. Users can select verbosity levels (e.g., concise, moderate, detailed) to control the amount of information provided, allowing the system to adapt between information completeness and power consumption in real-time

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system applies different description strategies to different parts of an image based on their importance. By identifying and prioritizing salient objects and regions, the system provides detailed descriptions for important elements while omitting or simplifying descriptions of less important elements, thus balancing information completeness with processing resources

Inventive Principle:

Principle #3Local quality

2Ease of operation

If screen readers provide detailed image descriptions, then user experience is improved, but processing time and computational resources increase

Engineering Contradiction:

Improveuser experienceVSAvoidprocessing efficiency

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The system segments the image description task into identifying salient objects, generating descriptions for each object, and assembling the final description. This segmentation allows the system to process images more efficiently by focusing computational resources on the most important elements rather than analyzing every pixel and object in detail

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs partial action by generating only the necessary level of detail required for effective communication. Instead of always providing exhaustive descriptions, the system adjusts the depth of analysis based on the image content and user needs, avoiding unnecessary computational overhead while maintaining adequate user experience

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12531052B2Image description generation for a screen reader based on a setting indicating a level of verbosity

Publication Date: 2026.01.20 CAPITAL ONE SERVICES LLC

AI summary

In some implementations, a browser extension may receive a setting indicating a level of verbosity and may receive an image and a set of words associated with the image. The browser extension may identify a foreground of the image and a background of the image and may identify, within the foreground of the image, a set of objects. The browser extension may rank the set of objects based on one or more properties of the set of objects and the set of words and may select a subset of objects from the set of objects based on the setting and the ranking. Accordingly, the browser extension may generate descriptions of the selected subset of objects based on the setting and may input the generated descriptions to a text to speech algorithm.