People with Visual Impairment Training Personal Object Recognizers: Feasibility and Challenges
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Blind people often need to identify objects around them, from packages of food to items of clothing. Automatic object recognition continues to provide limited assistance in such tasks because models tend to be trained on images taken by sighted people with different background clutter, scale, viewpoints, occlusion, and image quality than in photos taken by blind users. We explore personal object recognizers, where visually impaired people train a mobile application with a few snapshots of objects of interest and provide custom labels. We adopt transfer learning with a deep learning system for user-defined multi-label k-instance classification. Experiments with blind participants demonstrate the feasibility of our approach, which reaches accuracies over 90% for some participants. We analyze user data and feedback to explore effects of sample size, photo-quality variance, and object shape; and contrast models trained on photos by blind participants to those by sighted participants and generic recognizers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Media and Technology Usage and Attitudes Scale: An empirical investigation
Rosen, L. D., Whaling, K., Carrier, L. M., Cheever, N. A., & Rokkum, J. (2013) · Computers in Human Behavior · doi:10.1016/j.chb.2013.06.006 · Cited by 788
Cited by
Morrison, C., Cutrell, E., Dhareshwar, A., Doherty, K., Thieme, A., & Taylor, A. (2017) · Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3132525.3132530 · Cited by 69
“Others have looked at object identification more directly through a proposal for a personalized object detector [27]; studies understanding image capture for object identification [32]; as well as design experiments to understand object identification for people with low vision [59].”
BackgroundZhao, Y., Wu, S., Reynolds, L., & Azenkot, S. (2017) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3134756 · Cited by 68
“[34] tried to address this problem by designing personal object recognizers that enable visually impaired people to train recognition models with a few snapshots.”
BackgroundBrowseWithMe: An Online Clothes Shopping Assistant for People with Visual Impairments
Stangl, A. J., Kothari, E., Jain, S. D., Yeh, T., Grauman, K., & Gurari, D. (2018) · Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3234695.3236337 · Cited by 66
Brain-Machine Interfaces to Assist the Blind
Ptito, M., Bleau, M., Djerourou, I., Paré, S., Schneider, F. C., & Chebat, D.-R. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.638887 · Cited by 45
Theodorou, L., Massiceti, D., Zintgraf, L., Stumpf, S., Morrison, C., Cutrell, E., Harris, M. T., & Hofmann, K. (2021) · Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3441852.3471225 · Cited by 42
Misfitting With AI: How Blind People Verify and Contest AI Errors
Alharbi, R., Lor, P., Herskovitz, J., Schoenebeck, S., & Brewer, R. N. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675659 · Cited by 40
“Nevertheless, there is an exciting trend in research that aims to empower blind people in shaping personalized object recognition [4, 68].”
Morrison, C., Grayson, M., Marques, R. F., Massiceti, D., Longden, C., Wen, L., & Cutrell, E. (2023) · The 25th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3597638.3608395 · Cited by 38
“Find My Things can be seen as a relatively simple example of the way teachable AI can broaden an AI system – object recognition in this case – to meet the needs of a more diverse set of users.”
InfluentialToward User-Driven Sound Recognizer Personalization with People Who Are d/Deaf or Hard of Hearing
Goodman, S. M., Liu, P., Jain, D., McDonnell, E. J., Froehlich, J. E., & Findlater, L. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3463501 · Cited by 33
Everyday Uncertainty: How Blind People Use GenAI Tools for Information Access
Tang, X., Abdolrahmani, A., Gergle, D., & Piper, A. M. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713433 · Cited by 30
Blind Users Accessing Their Training Images in Teachable Object Recognizers
Hong, J., Gandhi, J., Mensah, E. E., Zeraati, F. Z., Jarjue, E., Lee, K., & Kacorri, H. (2022) · Proceedings of the 24th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3517428.3544824 · Cited by 22
Self-citationAdvocacy as Access Work: How People with Visual Impairments Gain Access to Digital Banking in India
Kameswaran, V., Y, V., & Marathe, M. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579596 · Cited by 22
Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges
Hong, J., & Kacorri, H. (2024) · The 26th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3663548.3675635 · Cited by 14
Self-citationSearching for the Non-Consequential: Dialectical Activities in HCI and the Limits of Computers
Zhang, H. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641945 · Cited by 12
Mack, K., McDonnell, E., Jain, D., Lu Wang, L., E. Froehlich, J., & Findlater, L. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445412 · Cited by 7
“[70], for example, compared images taken by blind and sighted users to “explore the benefits of having a sighted person training a blind user’s personal object recognizer.”
BackgroundGarg, K., Tang, X., Heo, J., Morgan, D. R., Gergle, D., Sudderth, E. B., & Piper, A. M. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791309 · Cited by 3
“This detailed, validated labeling is distinct from coarse object and product labels in prior work [55, 66].”
InfluentialCripping AI: Reimagining AI Through Lived Disability Experiences
Tang, X., Lin, T.-A., Li, J., & Wu, S. (2026) · Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3805689.3806744 · Cited by 2
Metadata
- Authors
- Kacorri, H., Kitani, K. M., Bigham, J. P., & Asakawa, C.
- Venue
- Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2017-05-02
- Pages
- 5839-5849
- OpenAlex
- W2611577320
- Cited by
- 115
- References
- 1
- FWCI
- 29.37
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.