Hand Gesture Recognition System for Games
Bibliographic record
Abstract
Video games are among the most popular forms of entertainment in the modern world. However, many gamers with physical disabilities are impeded by traditional controllers. While accessories such as foot pedals and enlarged buttons exist, many accessible gaming setups can end up costing hundreds of dollars. The solution to this problem must be obtainable by gamers of all demographics, and ideally, incorporate items most people already own. The Hand Gesture Recognition System for Games comes to the rescue. Most laptop computers and many desktops come equipped with a webcam, so naturally, that would be the starting point. Users would be able to perform various hand gestures, with each being mapped to a set of button combinations on a virtual gamepad. As gesture detection would have to be done in real-time, fast Computer Vision libraries such as OpenCV are needed to process images. This establishes the basis for the research, a program that can be deployed on any computer with a webcam to instantly create a gamepad out of thin air. The final program features an intuitive user interface with customizable game profiles that can be saved to or loaded from storage. The program captures webcam input 60 times per second, performing multiple levels of processing on each image. Using techniques such as thresholding, gaussian blurring, and grayscale conversion, an ideal image is fed to OpenCV’s contour detection algorithm. By calculating the angles between contours, the number of fingers held up can be determined. When a gesture is detected, the program communicates with a kernel-mode driver to send controller inputs directly to games. The result is a low latency controller with real-world applications. This research work is designed to enabling user customization allows for any Xinput compatible game to be controlled. This allowed for the implementation of not just racing games and driving simulators, but also first-person shoots and side-scrolling platformers.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.046 | 0.039 |
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".