C3 / LITERACY / EVALUATED AGES 6–8
Every letter begins with movement.
The mobile camera tracks a fingertip moving through free space. An ordered trajectory becomes the input to CNN-based letter recognition.
AI Air-Writing Trajectory Tracking
Illustrative playback. The research uses camera-based free-space writing; this visual is not a recognition model.
THE LEARNING PROBLEM
What this component
helps learners explore.
A finished character image loses the order and direction of movement. Free-space trajectories preserve that information for letter-learning interaction.
Technical approach
Hand-landmark tracking follows the index fingertip. Preprocessing normalizes location and scale before CNN-based recognition. The pipeline attends to path, start position, sequence and direction; this website’s playback is only an illustration.
FROM INPUT TO REINFORCEMENT
The learning workflow.
- 01
Capture the learner’s hand with the mobile camera
- 02
Track the index fingertip in free space
- 03
Normalize the ordered trajectory
- 04
Return a predicted letter and confidence
- 05
Provide feedback and record attempts, strokes and timing
SUPPORTED SCOPE
Purposeful boundaries.
- Implemented: uppercase and lowercase English letters
- Evaluated: 25 trials sampling 17 uppercase targets
- Genuine camera input in the research application
Pilot evaluation
19 correct predictions, three incorrect predictions and three failed letter returns. Mean total session time was 8.35 seconds; mean drawing time was 5.05 seconds.
What the findings do not establish
This is not a full A–Z/a–z benchmark. Recognition results do not independently establish stroke-correction effectiveness.
Source: Manuscript pp. 3–5. Read the manuscript ↗
Download individual proposal ↓LET’S EXPLORE WHAT’S NEXT
Bring a new dimension
to learning.
Start a conversation about a demonstration, school pilot or research partnership.