Related Experiment Video
Updated: Nov 17, 2025
07:12
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
Published on: April 11, 2025
688
Towards Making Videos Accessible for Low Vision Screen Magnifier Users
Ali Selman Aydin1, Shirin Feiz1, Vikas Ashok2
1Stony Brook University.
IUI. International Conference on Intelligent User Interfaces
|February 11, 2021
Summary
This study introduces SViM, a novel screen magnifier interface that uses computer vision to identify important video regions for people with low vision. SViM improves the video viewing experience for low vision screen magnifier users.
Area of Science:
- Human-Computer Interaction
- Computer Vision
- Assistive Technology
Background:
- Users with low vision face challenges with dynamic video content when using screen magnifiers.
- Manually panning and zooming screen magnifiers is difficult with rapidly changing video frames.
Purpose of the Study:
- To present SViM, a screen-magnifier interface designed to enhance video accessibility for low vision users.
- To leverage video saliency models for automatic identification of regions of interest (ROIs) in videos.
Main Methods:
- Developed SViM, a screen-magnifier interface integrating computer vision and video saliency models.
- Implemented features for zooming, switching between ROIs, and assistive panning.
- Conducted a user study with 13 low vision screen magnifier users.
Main Results:
- SViM automatically identifies salient regions of interest (ROIs) in videos.
- Users can interact with ROIs through zooming, clicking, and assistive panning.
- The study demonstrated a better user experience with SViM compared to existing screen magnifiers.
Conclusions:
- SViM shows promise in making video content more accessible for low vision screen magnifier users.
- The integration of computer vision significantly improves interaction with dynamic digital content.
