AI-Vision: A Three-Layer Accessible Image Exploration System for People with Visual Impairments in China

Kaixing Zhao, Rui Lai, Bin Guo, Le Liu, Liang He, Yuhang Zhao

科研成果: 期刊稿件文章同行评审

摘要

Accessible image exploration systems are able to help people with visual impairments (PVI) to understand image content by providing different types of interactions. With the development of computer vision technologies, image exploration systems are supporting more fine-grained image content processing, including image segmentation, description and object recognition. However, in developing countries like China, it is still rare for PVI to widely rely on such accessible system. To better understand the usage situation of accessible image exploration system in China and improve the image understanding of PVI in China, we developed AI-Vision, an Android based hierarchical accessible image exploration system supporting the generations of image general description, local object description and metadata information. Our 7-day diary study with 10 PVI verified the usability of AI-Vision and also revealed a series of design implications for improving accessible image exploration systems similar to AI-Vision.

源语言英语
文章编号ART145
期刊Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
8
3
DOI
出版状态已出版 - 9 9月 2024

指纹

探究 'AI-Vision: A Three-Layer Accessible Image Exploration System for People with Visual Impairments in China' 的科研主题。它们共同构成独一无二的指纹。

引用此