Netravani : AI based System for Translating Eye Movements into Speech
Bibliographic record
Abstract
Visually impaired people continue to struggle with making sense of the world around them and interpreting social signs, often exacerbated by the expense and internet requirement of current aid technologies. This work presents NETRAVANI, a low- cost AI powered smart glasses system designed to provide real-time assistive to visually impaired. The system integrates object detection, optical character recognition (OCR), facial emotion recognition, and text-speech-conversion having wearability, and compactness in mind. Developed using Raspberry Pi, embedded vision models, speech synthesis tools. Netravanni functions completely offline, enabling effortless operation in remote and low – resources environments. By translation visual and emotional cues into audio feedback, Netreavani increases autonomy impairments and fosters, more meaningful human interactions. The proposed system the facial emotion recognition module is able to achieve approximately 70% accuracy at 8 FPS inference speed, and the scene description module achieves BLEU-1 ≈ 0.65 and METEOR ≈ 0.52. By providing real-time context-sensitive audio feedback, NetraVaani provides an inexpensive, accessible, and offline assistive tool for enhancing social interaction and environmental perception in visually impaired users.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.010 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".