A Deep Learning Framework for Virtual Drawing and Geometric Shape Prediction Using Convolutional Neural Networks
Bibliographic record
Abstract
Hand gesture-based interaction provides a natural and effortless user experience to facilitate human-to-machine natural communication. This paper describes a deep learning approach for virtual drawing and geometric shape prediction based on computer vision and Convolutional Neural Networks (CNNs). The designed system combines real-time hand tracking, virtual canvas display, and a CNN-based classification model to identify user-drawn shapes through gestures. First, shapes on the virtual canvas are pre-processed—cropped, converted to grayscale, and resized-to provide consistent input for training. The CNN structure includes several convolutional and maxpooling layers, activated by ReLU and Softmax functions, to efficiently extract and classify shape features. The network is trained on a labeled training set of eight geometric shape classes, allowing it to learn subtle visual patterns. Training is accomplished by optimizing the network parameters via the backpropagation algorithm in order to reduce classification errors. Performance testing on an independent test set shows impressive results, where the model scores 98.37% accuracy. Important measures like precision and recall also support its efficacy. The learned model is integrated into a real-time virtual painting system, enabling users to draw and recognize freehand shapes without touch. The system enables applications in digital art, education, and gesture-based user interfaces, promoting humancomputer interaction. Future improvements can include multishape recognition, gesture-based color picking, and integration with augmented reality (AR) platforms.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".