TactileNet: Bridging the Accessibility Gap with AI-Generated Tactile Graphics for Individuals with Vision Impairment

2025-04-07

AI Summary

To address the global shortage of tactile graphics for 43 million visually impaired individuals and the labor-intensive, non-standardized nature of conventional production methods, this work introduces the first large-scale dataset and end-to-end AI framework for tactile graphic generation. Our method innovatively combines LoRA and DreamBooth fine-tuning techniques to adapt Stable Diffusion for text-driven, high-fidelity tactile image synthesis. We further propose the first quality assessment and filtering pipeline compliant with ISO/IEC tactile graphic standards. The framework generates 32,000 tactile images—including 7,050 high-quality outputs—spanning 66 educational categories. Expert evaluation confirms a 92.86% compliance rate with accessibility standards and 100% alignment of critical structural elements (e.g., pose and salient features). The approach supports fine-grained prompt editing and cross-category scalable generation, substantially improving both the efficiency and accessibility of tactile educational resource creation.

Technology Category

• Humans and AI: AI for Accessibility
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tactile graphics are essential for providing access to visual information for the 43 million people globally living with vision loss, as estimated by global prevalence data. However, traditional methods for creating these tactile graphics are labor-intensive and struggle to meet demand. We introduce TactileNet, the first comprehensive dataset and AI-driven framework for generating tactile graphics using text-to-image Stable Diffusion (SD) models. By integrating Low-Rank Adaptation (LoRA) and DreamBooth, our method fine-tunes SD models to produce high-fidelity, guideline-compliant tactile graphics while reducing computational costs. Evaluations involving tactile experts show that generated graphics achieve 92.86% adherence to tactile standards and 100% alignment with natural images in posture and features. Our framework also demonstrates scalability, generating 32,000 images (7,050 filtered for quality) across 66 classes, with prompt editing enabling customizable outputs (e.g., adding/removing details). Our work empowers designers to focus on refinement, significantly accelerating accessibility efforts. It underscores the transformative potential of AI for social good, offering a scalable solution to bridge the accessibility gap in education and beyond.

Problem

• AI-generated tactile graphics for vision impairment accessibility
• Overcoming labor-intensive traditional tactile graphic creation methods
• Scalable AI framework for high-fidelity, guideline-compliant tactile graphics

Innovation

• AI-driven framework for tactile graphics generation
• Uses Stable Diffusion with LoRA and DreamBooth
• Scalable solution with 92.86% adherence to standards