A Face Recognition Application for People with Visual Impairments

Zhao, Yuhang; Wu, Shuo; Reynolds, Lindsay; Azenkot, Shiri

doi:10.1145/3173574.3173789

Cited by 64 publications

(35 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature on assistive technologies for low vision and blind users is large. It spans from the early work on web accessibility [23], to more recent work on readability for screen readers [24], electronic white canes [25] and emerging systems that help in identifying people through face recognition [26]. To enable individuals through education, a substantial effort has been invested in assistive technologies for blind in the context of learning, especially targeting children [27].…”

Section: Related Workmentioning

confidence: 99%

A glimpse into smartphone screen reader use among blind teenagers in rural Nepal

Sankhi

Sandnes

2020

Disability and Rehabilitation: Assistive Technology

View full text Add to dashboard Cite

Purpose: Access to appropriate assistive technology is a challenge worldwide and especially in low GDPper-capita countries. Nepal is one example of a country with several coinciding challenges: some claim having a high rate of blindness in the general population, a low-GDP-per capita and some studies claim it has a low literacy rate, especially in rural areas. Without appropriate assistive technology, some disabled youth may not get full access to education. Methods: To gain insight into assistive technology use in rural Nepal, five blind teenagers in a mixed secondary school with disabled and non-disabled students in rural Nepal were interviewed about their daily smartphone use. Results: The results show that all the participants used screen readers on donated smartphones. None of the participants had received formal training in using smartphone screen readers and therefore lacked knowledge about basic and essential operational aspects of the devices as well as misguided expectations about the technology. Conclusions: One implication of the findings is that smartphone accessibility features training material needs to be made easily available to schools and all disabled youth worldwide, as smartphones are increasingly becoming available in low-income remote regions with low literacy rates. The built-in accessibility features of smartphones promise disabled youth a non-stigmatizing platform for social participation and access to the information society. ä IMPLICATIONS FOR REHABILITATION The built-in accessibility features of smartphones provide disabled youth a non-stigmatizing practical platform for social participation and access to education. Training material on how to use smartphone accessibility features needs to be made easily available to schools and all disabled youth worldwide.

show abstract

Section: Related Workmentioning

confidence: 99%

A glimpse into smartphone screen reader use among blind teenagers in rural Nepal

Sankhi

Sandnes

2020

Disability and Rehabilitation: Assistive Technology

View full text Add to dashboard Cite

show abstract

“…The design and use of ATs is a now established thread of research in HCI. Relevant, for example, are projects that have used computer vision to support people with vision impairments to complete tasks like identifying objects, people, and the contents of photos on social media [8], [40], [41], [49], [53], [78], [88], [90], [91], [92], [93], [94], [95]. For example, VizWiz [8] allowed blind people to photograph images for algorithms or crowd workers to describe.…”

Section: Ai Ats and Social Interactionsmentioning

confidence: 99%

“…A somewhat overlapping and formative thread of research is work examining how people with vision impairments (and passersby) make sense of and interact in social situations [1], [10], [11], [56], [76], [77], [79], [80], [86], [95], and whether this might offer opportunities to make greater use of one's senses in conjunction with the adaptive and learning capabilities of AI [3], [58], [65], [78], [92], [95]. In two separate studies, Thieme et al [80] and Williams et al [86] accompanied people with vision impairments on social and navigation activities, examining the myriad ways people work together and triangulate cues from their traveling companions, technologies, and environments to get where they want to go and, critically, to enjoy themselves.…”

Section: Ai Ats and Social Interactionsmentioning

confidence: 99%

“…In the data driven approaches popular in contemporary AI systems and being introduced into ATs [4], [8], [27], [40], [41], [49], [53], [58], [78], [88], [90], [91], [92], [93], [94], [95] these mundane attunements present a challenge. When what matters in the work of access is open, attuned in response to so many contingencies, how do we find datasets that might afford aggregation in any meaningful sense and that lead to the identification of actionable patterns of interaction that aren't too general?…”

Section: Mundane Attunementmentioning

confidence: 99%

See 1 more Smart Citation

The Care Work of Access

Bennett

Rosner

Taylor

2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Current approaches to AI and Assistive Technology (AT) often foreground task completion over other encounters such as expressions of care. Our paper challenges and complements such task-completion approaches by attending to the care work of access-the continual affective and emotional adjustments that people make by noticing and attending to one another. We explore how this work impacts encounters among people with and without vision impairments who complete tasks together. We find that bound up in attempts to get things done are concerns for one another and how well people are doing together. Reading this work through emerging disability studies and feminist STS scholarship, we account for two important forms of work that give rise to access: (1) mundane attunements and (2) noninnocent authorizations. Together these processes work as sensitizing concepts to help HCI scholars account for the ways that intelligent ATs both produce access while sometimes subverting people with disabilities.

show abstract

“…This high cost makes it particularly problematic when people with sensory disabilities are not able to determine the accuracy of a system's recognition result. As a consequence, users may place too much trust in the system (e.g., tending to trust inaccurate image description results [14]), or may resort to workarounds that have other negative consequences such as limiting independence (e.g., asking sighted people to double check the system's output) [22]. Thus, one important research question is how to support people with sensory disabilities in independently determining the quality and uncertainty (e.g., confidence level) of AI sensing results.…”

Section: Data and Model (In)accessibilitymentioning

confidence: 99%

Fairness issues in AI systems that augment sensory abilities

Findlater

Goodman

Zhao

et al. 2020

SIGACCESS Access. Comput.

Self Cite

View full text Add to dashboard Cite

Systems that augment sensory abilities are increasingly employing AI and machine learning (ML) approaches, with applications ranging from object recognition and scene description tools for blind users to sound awareness tools for d/Deaf users. However, unlike many other AI-enabled technologies, these systems provide information that is already available to non-disabled people. In this paper, we discuss unique AI fairness challenges that arise in this context, including accessibility issues with data and models, ethical implications in deciding what sensory information to convey to the user, and privacy concerns both for the primary user and for others.

show abstract

A Face Recognition Application for People with Visual Impairments

Cited by 64 publications

References 41 publications

A glimpse into smartphone screen reader use among blind teenagers in rural Nepal

A glimpse into smartphone screen reader use among blind teenagers in rural Nepal

The Care Work of Access

Fairness issues in AI systems that augment sensory abilities

Contact Info

Product

Resources

About