ReCog: Supporting Blind People in Recognizing Personal Objects
Dragan Ahmetovic, Daisuke Sato, Uran Oh, Tatsuya Ishihara, Kris Kitani, Chieko Asakawa
Abstract
We present ReCog, a mobile app that enables blind users to recognize objects by training a deep network with their own photos of such objects. This functionality is useful to differentiate personal objects, which cannot be recognized with pre-trained recognizers and may lack distinguishing tactile features. To ensure that the objects are well-framed in the captured photos, ReCog integrates a camera-aiming guidance that tracks target objects and instructs the user through verbal and sonification feedback to appropriately frame them.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get edf9048f-20e2-42dc-8cb8-31f2bc92e974Cited by top-tier papers7
- WorldScribe: Towards Context-Aware Live Visual DescriptionsRuei-Che Chang, Yuxuan Liu, Anhong GuoUIST 2024 · 54 citations
- Beyond Visual Perception: Insights from Smartphone Interaction of Visually Impaired Users with Large Multimodal ModelsJingyi Xie, Rui Yu, He Zhang, Syed Masum Billah et al.CHI 2025 · 40 citations
- "I Shake The Package To Check If It's Mine": A Study of Package Fetching Practices and Challenges of Blind and Low Vision People in ChinaWentao Lei, Mingming Fan, Juliann ThangCHI 2022 · 13 citations
- Exploring Aiming Techniques for Blind People in Virtual RealityJoão Mendes, Manuel Piçarra, Inês Gonçalves, André Rodrigues et al.IEEE VR 2025 · 3 citations
- "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language ModelsKapil Garg, Xinru Tang, Jimin Heo, Dwayne R. Morgan et al.CHI 2026 · 2 citations
Related papers
- The ORBIT India Dataset: Understanding the Challenges of Collecting a Disability-First AI Dataset in Low-Resource EnvironmentsGesu India, Martin Grayson, Cecily Morrison, Daniela Massiceti et al.CHI 2026 · 1 citation
- VRSight: An AI-Driven Scene Description System to Improve Virtual Reality Accessibility for Blind PeopleDaniel Killough, Justin Feng, Zheng Xue "ZX" Ching, Daniel Wang et al.UIST 2025 · 3 citations
- ORBIT: A Real-World Few-Shot Dataset for Teachable Object RecognitionDaniela Massiceti, Luisa M. Zintgraf, John Bronskill, Lida Theodorou et al.ICCV 2021 · 55 citations
- Data-driven accessibility repair revisited: on the effectiveness of generating labels for icons in Android appsForough Mehralian, Navid Salehnamadi, Sam MalekFSE 2021 · 47 citations
- Hand Gesture Recognition for Blind Users by Tracking 3D Gesture TrajectoryPrerna Khanna, I. V. Ramakrishnan, Shubham Jain, Xiaojun Bi et al.CHI 2024 · 6 citations
