How sayali-mhalaskar/sign-language-detection works
This repository supports a webcam-based A–Z sign-recognition workflow and a separate data-preparation/training workflow. In the web app, a browser starts the camera and requests a video stream; frames are converted to hand landmarks, classified, and shown as signs or sentence text. Sentence controls edit the accumulated text. Data can be collected from a webcam or extracted from images, then used to train the classifier. The runtime implementation is in tempCodeRunnerFile.py; README capabilities not visible in that excerpt are retained where documented, but their wiring is not assumed.
Main entry points: tempCodeRunnerFile.py Flask application · data_collection.py Webcam collector · train_model.py Classifier trainer · to_create_csv.py Image landmark export
Components 15
Data preparation
- Webcam collector
data_collection.py - Image landmark export
to_create_csv.py - Landmark CSV
Model training
- Classifier trainer
train_model.py - Trained classifier
Recognition runtime
- Hand landmarks
tempCodeRunnerFile.py - Sign classification
tempCodeRunnerFile.py - Sentence state
tempCodeRunnerFile.py
Web interface
- Flask application
tempCodeRunnerFile.py - Recognition page
templates/index.html - Frame stream
tempCodeRunnerFile.py - Sentence controls
tempCodeRunnerFile.py
Other components
- User browser
- Webcam
- MediaPipe Hands
Connections 17
- Webcam collector → Webcam: captures frames
data_collection.py - Webcam collector → Landmark CSV: writes samples
data_collection.py - Image landmark export → Landmark CSV: writes landmarks
to_create_csv.py - Classifier trainer → Landmark CSV: reads data
train_model.py - Classifier trainer → Trained classifier: saves model
train_model.py - User browser → Flask application: sends requests
tempCodeRunnerFile.py - Flask application → Recognition page: renders page
tempCodeRunnerFile.py - Flask application → Webcam: opens camera
tempCodeRunnerFile.py - Flask application → Frame stream: serves stream
tempCodeRunnerFile.py - Frame stream → Webcam: reads frames
tempCodeRunnerFile.py - Frame stream → Hand landmarks: preprocesses frames
tempCodeRunnerFile.py - Hand landmarks → MediaPipe Hands: detects hands
tempCodeRunnerFile.py - Frame stream → Sign classification: classifies landmarks
tempCodeRunnerFile.py - Sign classification → Trained classifier: runs prediction
tempCodeRunnerFile.py - Frame stream → Sentence state: updates text
tempCodeRunnerFile.py - Flask application → Sentence controls: routes edits
tempCodeRunnerFile.py - Sentence controls → Sentence state: edits text
tempCodeRunnerFile.py