Real-time Scene Text Detection with Differentiable Binarization
Paper • 1911.08947 • Published
DBNet Khmer Text Detector
A DBNet (Differentiable Binarization) text detection model for Khmer/English documents — MobileNetV3 backbone + FPN + DBHead. Detects bounding boxes around text lines; it does not perform OCR/recognition.
Trained from scratch on synthetic Cambodian-style documents (plain docs, ID cards, official letters). See dbnet-text-detector for the full training pipeline, data generators, and inference code.
Files
| File | Description |
|---|---|
khmer_dbnet_mobilenetv3.onnx |
Portable ONNX export — recommended for inference (torch-free, via onnxruntime) |
khmer_dbnet_mobilenetv3.pth |
PyTorch checkpoint (weights + training config) — for fine-tuning or DBNet.pytorch-based inference |
Usage
pip install dbnet-text-detector
from dbnet_detector import DBNetDetector
detector = DBNetDetector.from_pretrained("Darayut/dbnet-khmer")
boxes = detector.detect("your_image.jpg")
Weights are downloaded from this repo on first use and cached locally
(~/.cache/huggingface/hub).
Metrics
F1 0.987 on held-out synthetic validation data (v1 dataset). See the GitHub repo's
DOCUMENTATION.md for full training/eval details.
License
MIT
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support