Towards making videos accessible for low vision screen magnifier users

Aydın, Ali Selman; Feiz, Shirin; Ashok, Vikas; Ramakrishnan, I. V.

doi:10.1145/3377325.3377494

Cited by 17 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A group of researchers recently developed a screen-magnifier interface that is able to identify salient regions of interest through image processing, and allows the user to control the zoom of the identified (salient) objects with mouse clicks. 52 They tested the device in a study of participants with CVL, and those users expressed a preference for this technique over traditional, simple magnification techniques. Salience-defined magnification centre 52 and giving the viewer the option to turn magnification on and off 50,51 (or up and down) is worthy of future study.…”

Section: Discussionmentioning

confidence: 99%

“…52 They tested the device in a study of participants with CVL, and those users expressed a preference for this technique over traditional, simple magnification techniques. Salience-defined magnification centre 52 and giving the viewer the option to turn magnification on and off 50,51 (or up and down) is worthy of future study.…”

Section: Discussionmentioning

confidence: 99%

“…Thus, we have not pursued those approaches so far. A group of researchers recently developed a screen‐magnifier interface that is able to identify salient regions of interest through image processing, and allows the user to control the zoom of the identified (salient) objects with mouse clicks 52 . They tested the device in a study of participants with CVL, and those users expressed a preference for this technique over traditional, simple magnification techniques.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

An implementation of Bubble Magnification did not improve the video comprehension of individuals with central vision loss

Costela

Reeves

Woods

2021

Ophthalmic Physiologic Optic

View full text Add to dashboard Cite

Purpose: People with central vision loss (CVL) watch television, videos and movies, but often report difficulty and have reduced video comprehension. An approach to assist viewing videos is electronic magnification of the video itself, such as Bubble Magnification. Methods: We created a Bubble Magnification technique that displayed a magnified segment around the centre of interest (COI) as determined by the gaze of participants with normal vision. The 15 participants with CVL viewed video clips shown with 2× and 3× Bubble Magnification, and unedited. We measured video comprehension and gaze coherence. Results: Video comprehension was significantly worse with both 2× (p = 0.01) and 3× Bubble Magnification (p < 0.001) than the unedited video. There was no difference in gaze coherence across conditions (p ≥ 0.58). This was unexpected because we expected a benefit in both video comprehension and gaze coherence. This initial attempt to implement the Bubble Magnification method had flaws that probably reduced its effectiveness. Conclusions: In the future, we propose alternative implementations of Bubble Magnification, such as variable magnification and bubble size. This study is a first step in the development of an intelligent-magnification approach to providing a vision rehabilitation aid to assist people with CVL.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

An implementation of Bubble Magnification did not improve the video comprehension of individuals with central vision loss

Costela

Reeves

Woods

2021

Ophthalmic Physiologic Optic

View full text Add to dashboard Cite

show abstract

“…We conducted a user study with 13 participants to assess effectiveness of SViM system [6], in which we compared the three prototypes we developed to the Windows screen magnifier [2] and VLC Player magnifier [5]. Both subjective results and our measurements have demonstrated that the users had a better experience with SViM interfaces compared to the baseline magnifiers.…”

Section: Discussionmentioning

confidence: 99%

A saliency-driven video magnifier for people with low vision

Aydın

Feiz

Ashok

et al. 2020

Proceedings of the 17th International Web for All Conference

Self Cite

View full text Add to dashboard Cite

Consuming video content poses significant challenges for many screen magnifier users, which is the "go to" assistive technology for people with low vision. While screen magnifier software could be used to achieve a zoom factor that would make the content of the video visible to low-vision users, it is oftentimes a major challenge for these users to navigate through videos. Towards making videos more accessible for low-vision users, we have developed the SViM video magnifier system [6]. Specifically, SViM consists of three different magnifier interfaces with easy-touse means of interactions. All three interfaces are driven by visual saliency as a guided signal, which provides a quantification of interestingness at the pixel-level. Saliency information, which is provided as a heatmap is then processed to obtain distinct regions of interest. These regions of interests are tracked over time and displayed using an easy-to-use interface. We present a description of our overall design and interfaces. CCS CONCEPTS • Human-centered computing ~ Accessibility technologies KEYWORDS Screen magnifier users, video accessibility Figure 1: Top: Original image. Bottom: Heatmap and sample ROIs(Photo at the top is derived from video by Freestocks (CC BY 3.0)).

show abstract

“…Piano Genie [ 153 ] is an intelligent controller for non-musicians to improvise on the piano. SViM [ 154 ] is an adaptive screen-magnifier tool for people with low vision to watch videos. Lee et al [ 155 ] developed a tool to assess the quality of rehabilitation exercises.…”

Section: Classifying Hcml Researchmentioning

confidence: 99%

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Kaluarachchi

Reis

Nanayakkara

2021

Sensors

View full text Add to dashboard Cite

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

show abstract

Towards making videos accessible for low vision screen magnifier users

Cited by 17 publications

References 32 publications

An implementation of Bubble Magnification did not improve the video comprehension of individuals with central vision loss

An implementation of Bubble Magnification did not improve the video comprehension of individuals with central vision loss

A saliency-driven video magnifier for people with low vision

A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Contact Info

Product

Resources

About