Sign Board Text detection using Faster R-CNN

Generate synthetic dataset for object detection (Faster R-CNN) + evaluate on real data

Methodology:

1. Create Synthetic Dataset comprising images and bounding box coordinates for Arabic and English texts.
2. Train a Faster RCNN model on the synthetic dataset
3. Collect a few real life examples of English and Arabic sign boards and evaluate the model

Generate images + bounding box dataset

generate_synthetic_dataset.py

Train on fake dataset

train_fasterrcnn.py

Evaluate on real dataset

eval_fasterrcnn.py

Synthetic Dataset Generation: Steps

Evaluation on Real Data