--- license: mit language: - fa library_name: onnxruntime pipeline_tag: image-to-text tags: - alpr - license-plate-recognition - ocr - persian - farsi - iranian-license-plate - crnn - ctc - yolo - onnx - object-detection ---

Platrix

# Platrix — Iranian License-Plate Recognition Models Production ONNX models for detecting and reading **Iranian vehicle license plates**, powering the [**Platrix**](https://github.com/AliAkrami1375/Platrix) real-time, self-hosted plate-surveillance system. > 📦 **Code & full pipeline:** https://github.com/AliAkrami1375/Platrix > 🤗 **This model repo:** https://huggingface.co/Dibachain/Platrix The pipeline is **two-stage**: a YOLO **detector** locates the plate in the frame, an image-quality **enhancement** step cleans the crop, then a segmentation-free **CRNN + CTC reader** reads the whole plate at once and returns the standard Iranian layout `DD L DDD DD` (two digits · letter · three digits · two-digit region), e.g. `۸۱ و ۶۳۸ ۱۳`. All models run with **ONNX Runtime** — no PyTorch or TensorFlow needed at inference time. --- ## 📊 Performance Measured on **220 real Iranian surveillance photos** (grayscale gate/road cameras — the hard, real-world domain, not staged shots).

A lightweight **secondary detector** runs only when the primary finds nothing. It recovers plates the primary is blind to — trucks, night shots, small/far and dim plates — lifting the end-to-end read rate from **95.9% → 97.7%** with **no regression** on the easy majority (the fallback fires on only ~2% of frames).

### Training curves

The reader reaches ~93% whole-plate accuracy in training and **~98% on real photos**; the detector reaches **mAP@0.5 ≈ 0.99** on held-out real frames. --- ## 📁 Files | File | Role | Input | Output | |------|------|-------|--------| | `plate_yolo.onnx` | **Plate detector** (YOLOv8, primary) | `1×3×H×W` RGB, letterboxed, `/255` | `1×5×N` → `cx,cy,w,h,conf` | | `plate_yolo_fallback.onnx` | **Secondary detector** — runs only when the primary finds nothing; recovers hard surveillance frames | `1×3×640×640` | `1×5×N` | | `ocr_crnn.onnx` | **Whole-plate reader** (CRNN+CTC) — *recommended* | `1×1×32×128` grayscale, `/255` | `1×T×(C+1)` logits (CTC, blank = last) | | `ocr_crnn.labels.json` | Class list for the CRNN (index → character) | — | 32 classes | | `ocr_cnn.onnx` | Per-character classifier (lightweight fallback reader) | `1×1×32×32` grayscale | class logits | | `ocr_cnn.labels.json` | Class list for the per-char classifier | — | — | **Character set (32 classes):** digits `0–9` and the Persian plate letters `ا ب ت ث ج ح د ز س ش ص ط ع ق ل م ن ه و پ ژ ی`. --- ## 🚀 Getting started ### Option A — Run the full Platrix system (recommended) The complete app (web dashboard, multi-camera streaming, watchlists, API) lives in the GitHub repo. It downloads these models for you. ```bash git clone https://github.com/AliAkrami1375/Platrix.git cd Platrix # fetch the models from this repo into ./models pip install -U "huggingface_hub[cli]" huggingface-cli download Dibachain/Platrix \ plate_yolo.onnx plate_yolo_fallback.onnx \ ocr_crnn.onnx ocr_crnn.labels.json ocr_cnn.onnx ocr_cnn.labels.json \ --local-dir models/ # then either: docker compose up --build # Docker # — or — python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt && pip install -e . platrix serve # dashboard at http://localhost:8080 ``` ### Option B — Use the models directly (ONNX Runtime) ```bash pip install onnxruntime opencv-python-headless numpy huggingface-cli download Dibachain/Platrix \ plate_yolo.onnx plate_yolo_fallback.onnx ocr_crnn.onnx ocr_crnn.labels.json \ --local-dir models/ ``` ```python import json, cv2, numpy as np, onnxruntime as ort # --- Reader (CRNN + CTC) --- labels = json.load(open("models/ocr_crnn.labels.json", encoding="utf-8")) blank = len(labels) # CTC blank is the last index crnn = ort.InferenceSession("models/ocr_crnn.onnx", providers=["CPUExecutionProvider"]) def read_plate(plate_bgr): g = cv2.cvtColor(plate_bgr, cv2.COLOR_BGR2GRAY) g = cv2.resize(g, (128, 32)).astype(np.float32) / 255.0 # 1x1x32x128 logits = crnn.run(None, {"input": g[None, None]})[0][0] # T x (C+1) ids, out, prev = logits.argmax(1), [], -1 for i in ids: # greedy CTC decode if i != blank and i != prev: out.append(labels[i]) prev = i return "".join(out) ``` **Two-stage flow:** run `plate_yolo.onnx` first (standard YOLOv8 letterbox pre-process + confidence/NMS post-process) to crop the plate, then pass the crop to `read_plate`. If the primary detector returns nothing, run `plate_yolo_fallback.onnx` at **640×640** as a second pass — it recovers the hard surveillance frames the primary is blind to. A few **real test photos** ship under [`img-test/`](./tree/main/img-test) so you can try it immediately. --- ## 🧠 How it works 1. **Detect** — YOLOv8 locates the plate; weak/non-plate boxes are ignored. 2. **Enhance** — the crop is upscaled, denoised, contrast-corrected and sharpened. The *same* enhancement is applied during training, so there is no train/serve mismatch — the enhancement genuinely helps instead of shifting the input. 3. **Read** — the segmentation-free CRNN reads the whole plate in one pass with a CTC head. It is trained on **real Iranian plate-character shapes**, so look-alike glyphs (e.g. the digit `۴` vs `۶`) are read correctly. Splitting a plate into individual characters is fragile on real photos (shadows, motion blur, tilt, dirt); reading the entire plate at once is far more robust. --- ## Intended use & limitations - **Intended for** lawful applications such as parking management, access control, gate automation and traffic analytics. - **Optimised for** standard private Iranian plates. Very low-resolution, heavily occluded or non-standard plates may reduce accuracy. - You are responsible for complying with the privacy and surveillance laws that apply to your deployment. --- ## Links - **Project & full pipeline:** https://github.com/AliAkrami1375/Platrix - **License:** MIT