Convolutional neural network for dactylological alphabet recognition of Honduran Sign Language (LESHO)
Bibliographic record
Abstract
Introduction The critical problem of hearing and speech difficulties among thousands of Hondurans is a latent need, and in search of tools that allow the inclusion of the population with this condition is sought through the introduction of a convolutional neural network (CNN) designed for real-time detection and classification of the dactyl alphabet of the Honduran sign language (LESHO). This study represents an important step forward in promoting accessibility and inclusion of the Honduran deaf community, which faces few technological solutions adapted to their needs. Methods A proprietary dataset comprising more than 8,000 images with various angles and gestures was meticulously constructed, ensuring robust training and evaluation of the model. Spiral research methodology was employed to iteratively refine network performance, with an emphasis on accuracy and real-time deployment capabilities. Results The final model showed exceptional results during the testing, achieving a mean average precision (mAP) of 98.8%, a precision of 97.4%, and a recall of 97.7%. These metrics underscore the reliability of the CNN in recognizing both static and dynamic gestures with minimal errors. Conclusion The model’s capacity to generalize indicates its potential for further applications, such as full sign language interpretation and expanded vocabulary training
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".