TactileEval: A Step Towards Automated Fine-Grained Evaluation and Editing of Tactile Graphics
Adnan Khan, Abbas Akkasi, Majid Komeili

TL;DR
TactileEval introduces an automated pipeline for fine-grained evaluation and editing of tactile graphics, leveraging expert annotations, a structured taxonomy, and AI models to improve quality and repair processes.
Contribution
The paper develops a novel taxonomy, gathers extensive annotations, trains a ViT-based classifier, and creates an AI-guided editing pipeline for tactile graphics quality improvement.
Findings
ViT classifier achieves 85.70% accuracy across tasks.
Taxonomy captures meaningful perceptual structure.
Automated editing pipeline produces targeted corrections.
Abstract
Tactile graphics require careful expert validation before reaching blind and visually impaired (BVI) learners, yet existing datasets provide only coarse holistic quality ratings that offer no actionable repair signal. We present TactileEval, a three-stage pipeline that takes a first step toward automating this process. Drawing on expert free-text comments from the TactileNet dataset, we establish a five-category quality taxonomy; encompassing view angle, part completeness, background clutter, texture separation, and line quality aligned with BANA standards. We subsequently gathered 14,095 structured annotations via Amazon Mechanical Turk, spanning 66 object classes organized into six distinct families. A reproducible ViT-L/14 feature probe trained on this data achieves 85.70% overall test accuracy across 30 different tasks, with consistent difficulty ordering suggesting the taxonomy…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
