Improving Web
Accessibility Using Visual
Saliency Models
VIKAS ASHOK
DEPARTMENT OF COMPUTER SCIENCE
OLD DOMINION UNIVERSITY
Scope of the Talk
 Web Accessibility
 People with Visual Impairments
 Visual Saliency
 Accessing Online Videos
 For Low Vision Screen-Magnifier Users
 SVIM – Saliency Driven Video Magnifier
 Webpage Navigation
 For Blind Screen-Reader Users
 SAIL – Saliency Driven Injection of ARIA Landmarks
Web
Accessibility
 “Web accessibility means that websites, tools, and technologies
are designed and developed so that people with disabilities can
use them. More specifically, people can:
 perceive, understand, navigate, and interact with the Web
 contribute to the Web”
- W3C
Improving Usability
Webpage Transcoding
Web Automation
Auxiliary Input Interfaces
Speech Assistants
• Audio-Haptic
• Dial
• Modify Webpages
Crowdsourcing
• Ask Others
• Voice Commands• Hand-Coded
Macros
Visual Saliency
Image source: Jiang, Lai, et al. "Deepvs: A deep learning based video saliency prediction approach." Proceedings of the
european conference on computer vision (eccv). 2018.
Saliency Driven
Low-Vision
Screen Magnifier
Video
Magnification
 Windows Magnifier
 Zoom + Pan with mouse
 Directly over content
VLC Magnifier
 Zoom + Pan with mouse
 Indirectly via thumbnail
SVIM ARCHITECTURE
Image source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
Saliency Detection
 DeepVS [1]
 Trained on a video saliency dataset (LEDOV)
 Object-to-motion CNN for incorporating objects and motion
 ConvLSTM layers for incorporating temporal information
Image source: [1] Jiang, Lai, et al. "Deepvs: A deep learning based video saliency prediction
approach." Proceedings of the european conference on computer vision (eccv). 2018.
Region of Interest (ROI) Detection
Clustering Salient Pixels
Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
Temporal
Tracking
 Kalman Filter Smoothing to
Handle Jitter
 Viewport adjusted only for
significant movements
Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
SVIM Interface Features
Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
SVIM
DEMO
Evaluation
Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
Evaluation
Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen
magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces.
2020.
Saliency Based
Automatic
Injection of ARIA
Landmarks
Webpage
Navigation with
Screen readers
Linear Navigation
 Tedious and Tiring:
 70 'p' or 9 'h' shortcuts to reach
the red box!
 Solution: ARIA landmarks
 Caveat: Not widely utilized
Image Source: Aydin, Ali Selman, et al. "SaIL: saliency-
driven injection of ARIA landmarks." Proceedings of the
25th International Conference on Intelligent User
Interfaces. 2020.
Saliency Based
Landmark
Injection
 Detect Salient Regions
 Filter Candidates
 Inject ARIA Landmarks
Image Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on
Intelligent User Interfaces. 2020.
Webpage
Saliency with
GANs
 SalGAN [1] originally trained
for image saliency, re-trained
to predict web saliency
[1] Pan, Junting, et al. "Salgan: Visual saliency prediction with adversarial networks." CVPR
Scene Understanding Workshop (SUNw). 2017.
Automatic Landmark Injection
Examples
Image Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on
Intelligent User Interfaces. 2020.
More Examples
Image Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on
Intelligent User Interfaces. 2020.
Evaluation
 C1 – Without SAIL
 C2 – With SAIL
Task Completion Time (Seconds)
Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on
Intelligent User Interfaces. 2020.
Concluding Remark
Visual Saliency Models Have Tremendous Potential For Improving
Usability For People With Visual Impairments
Thank You!

Improving Web Accessibility Using Visual Saliency

  • 1.
    Improving Web Accessibility UsingVisual Saliency Models VIKAS ASHOK DEPARTMENT OF COMPUTER SCIENCE OLD DOMINION UNIVERSITY
  • 2.
    Scope of theTalk  Web Accessibility  People with Visual Impairments  Visual Saliency  Accessing Online Videos  For Low Vision Screen-Magnifier Users  SVIM – Saliency Driven Video Magnifier  Webpage Navigation  For Blind Screen-Reader Users  SAIL – Saliency Driven Injection of ARIA Landmarks
  • 3.
    Web Accessibility  “Web accessibilitymeans that websites, tools, and technologies are designed and developed so that people with disabilities can use them. More specifically, people can:  perceive, understand, navigate, and interact with the Web  contribute to the Web” - W3C
  • 4.
    Improving Usability Webpage Transcoding WebAutomation Auxiliary Input Interfaces Speech Assistants • Audio-Haptic • Dial • Modify Webpages Crowdsourcing • Ask Others • Voice Commands• Hand-Coded Macros
  • 5.
    Visual Saliency Image source:Jiang, Lai, et al. "Deepvs: A deep learning based video saliency prediction approach." Proceedings of the european conference on computer vision (eccv). 2018.
  • 6.
  • 7.
    Video Magnification  Windows Magnifier Zoom + Pan with mouse  Directly over content VLC Magnifier  Zoom + Pan with mouse  Indirectly via thumbnail
  • 8.
    SVIM ARCHITECTURE Image source:Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 9.
    Saliency Detection  DeepVS[1]  Trained on a video saliency dataset (LEDOV)  Object-to-motion CNN for incorporating objects and motion  ConvLSTM layers for incorporating temporal information Image source: [1] Jiang, Lai, et al. "Deepvs: A deep learning based video saliency prediction approach." Proceedings of the european conference on computer vision (eccv). 2018.
  • 10.
    Region of Interest(ROI) Detection Clustering Salient Pixels Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 11.
    Temporal Tracking  Kalman FilterSmoothing to Handle Jitter  Viewport adjusted only for significant movements Source: Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 12.
    SVIM Interface Features Source:Aydin, Ali Selman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 13.
  • 14.
    Evaluation Source: Aydin, AliSelman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 15.
    Evaluation Source: Aydin, AliSelman, et al. "Towards making videos accessible for low vision screen magnifier users." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 16.
  • 17.
    Webpage Navigation with Screen readers LinearNavigation  Tedious and Tiring:  70 'p' or 9 'h' shortcuts to reach the red box!  Solution: ARIA landmarks  Caveat: Not widely utilized Image Source: Aydin, Ali Selman, et al. "SaIL: saliency- driven injection of ARIA landmarks." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 18.
    Saliency Based Landmark Injection  DetectSalient Regions  Filter Candidates  Inject ARIA Landmarks Image Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 19.
    Webpage Saliency with GANs  SalGAN[1] originally trained for image saliency, re-trained to predict web saliency [1] Pan, Junting, et al. "Salgan: Visual saliency prediction with adversarial networks." CVPR Scene Understanding Workshop (SUNw). 2017.
  • 20.
  • 21.
    Examples Image Source: Aydin,Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 22.
    More Examples Image Source:Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 23.
    Evaluation  C1 –Without SAIL  C2 – With SAIL Task Completion Time (Seconds) Source: Aydin, Ali Selman, et al. "SaIL: saliency-driven injection of ARIA landmarks." Proceedings of the 25th International Conference on Intelligent User Interfaces. 2020.
  • 24.
    Concluding Remark Visual SaliencyModels Have Tremendous Potential For Improving Usability For People With Visual Impairments
  • 25.

Editor's Notes

  • #5 To address this gap in interaction experiences between sighted and blind users, here are some of the popular approaches that people have taken-