DibaAi commited on
Commit
50bdc0c
·
1 Parent(s): 4f5a43e

Rename model card to Platrix; add img-test sample photos and cross-links

Browse files
README.md CHANGED
@@ -18,12 +18,15 @@ tags:
18
  - object-detection
19
  ---
20
 
21
- # ocr-persian — Iranian License-Plate Recognition Models
22
 
23
  Production ONNX models for detecting and reading **Iranian vehicle license
24
  plates**, powering the [**Platrix**](https://github.com/AliAkrami1375/Platrix)
25
  real-time, self-hosted plate-surveillance system.
26
 
 
 
 
27
  The pipeline is **two-stage**: a YOLO **detector** locates the plate in the
28
  frame, then a segmentation-free **CRNN + CTC reader** reads the whole plate at
29
  once and returns the standard Iranian layout `DD L DDD DD`
@@ -68,10 +71,13 @@ instead of shifting the input distribution.
68
 
69
  ```bash
70
  pip install onnxruntime opencv-python-headless numpy
71
- huggingface-cli download Dibachain/ocr-persian \
72
  plate_yolo.onnx ocr_crnn.onnx ocr_crnn.labels.json --local-dir models/
73
  ```
74
 
 
 
 
75
  ```python
76
  import json, cv2, numpy as np, onnxruntime as ort
77
 
 
18
  - object-detection
19
  ---
20
 
21
+ # Platrix — Iranian License-Plate Recognition Models
22
 
23
  Production ONNX models for detecting and reading **Iranian vehicle license
24
  plates**, powering the [**Platrix**](https://github.com/AliAkrami1375/Platrix)
25
  real-time, self-hosted plate-surveillance system.
26
 
27
+ > 📦 **Code & full pipeline:** https://github.com/AliAkrami1375/Platrix
28
+ > 🤗 **This model repo:** https://huggingface.co/Dibachain/Platrix
29
+
30
  The pipeline is **two-stage**: a YOLO **detector** locates the plate in the
31
  frame, then a segmentation-free **CRNN + CTC reader** reads the whole plate at
32
  once and returns the standard Iranian layout `DD L DDD DD`
 
71
 
72
  ```bash
73
  pip install onnxruntime opencv-python-headless numpy
74
+ huggingface-cli download Dibachain/Platrix \
75
  plate_yolo.onnx ocr_crnn.onnx ocr_crnn.labels.json --local-dir models/
76
  ```
77
 
78
+ A few **real test photos** ship in this repo under [`img-test/`](./tree/main/img-test)
79
+ so you can try recognition right away.
80
+
81
  ```python
82
  import json, cv2, numpy as np, onnxruntime as ort
83
 
img-test/sample-01.jpg ADDED
img-test/sample-02.jpg ADDED
img-test/sample-03.jpg ADDED
img-test/sample-04.jpg ADDED
img-test/sample-05.jpg ADDED
img-test/sample-06.jpg ADDED
img-test/sample-07.jpg ADDED
img-test/sample-08.jpg ADDED
img-test/sample-09.jpg ADDED
img-test/sample-10.jpg ADDED