Legibility of Videos with ASL signers
Raja S. Kushalnagar

TL;DR
This paper investigates how the size of sign language videos affects legibility, aligning findings with vision science and accessibility guidelines to inform optimal signer display sizes for viewers.
Contribution
It provides empirical analysis of signer size and legibility, connecting vision science principles with accessibility standards for sign language videos.
Findings
Signer size correlates with recognition ease.
Optimal signer size range is from 2 to 5 inches on a smartphone.
Vision science supports size recommendations for sign language videos.
Abstract
The viewing size of a signer correlates with legibility, i.e., the ease with which a viewer can recognize individual signs. The WCAG 2.0 guidelines (G54) mention in the notes that there should be a mechanism to adjust the size to ensure the signer is discernible but does not state minimum discernibility guidelines. The fluent range (the range over which sign viewers can follow the signers at maximum speed) extends from about 7{\deg} to 20{\deg}, which is far greater than 2{\deg} for print. Assuming a standard viewing distance of 16 inches from a 5-inch smartphone display, the corresponding sizes are from 2 to 5 inches, i.e., from 1/3rd to full-screen. This is consistent with vision science findings about human visual processing properties, and how they play a dominant role in constraining the distribution of signer sizes.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHearing Impairment and Communication · Hand Gesture Recognition Systems · Tactile and Sensory Interactions
