Dynamic Sign Language Recognition for Smart Home Interactive Application Using Stochastic Linear Formal Grammar
Bibliographic record
Abstract
This paper presents the state-of-the art dynamic sign language recognition (DSLR) system for smart home interactive applications. Our novel DSLR system comprises two main subsystems: an image processing (IP) module and a stochastic linear formal grammar (SLFG) module. Our IP module enables us to recognize the individual words of the sign language (i.e., a single gesture). In this module, we used the bag-of-features (BOFs) and a local part model approach for bare hand dynamic gesture recognition from a video. We used dense sampling to extract local 3-D multiscale whole-part features. We adopted 3-D histograms of a gradient orientation descriptor to represent features. The k-means++ method was applied to cluster the visual words. Dynamic hand gesture classification was conducted using the BOFs and nonlinear support vector machine methods. We used a multiscale local part model to preserve temporal context. The SLFG module analyzes the sentences of the sign language (i.e., sequences of gestures) and determines whether or not they are syntactically valid. Therefore, the DSLR system is not only able to rule out ungrammatical sentences, but it can also make predictions about missing gestures, which, in turn, increases the accuracy of our recognition task. Our IP module alone seals the accuracy of 97% and outperforms any existing bare hand dynamic gesture recognition system. However, by exploiting syntactic pattern recognition, the SLFG module raises this accuracy by 1.65%. This makes the aggregate performance of the DSLR system as accurate as 98.65%.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".