Plates

Detect. Crop. Read — for gates & lots.

Nhận diện biển số bằng YOLOv8 + EasyOCR. Landing + live browser OCR trên Azure F1; cùng engine trên Hugging Face static Space.

Pipeline

Built for real ALPR work, not slideware.

Same stack as the repo: Ultralytics detect, plate preprocess, EasyOCR allowlist, eval scripts.

01

Detect

YOLOv8 / OBB weights find plate boxes in frame — detect.py / detect_v2.py.

02

Crop & preprocess

Border trim, histogram equalization, 2× cubic upscale so OCR sees cleaner glyphs.

03

OCR

EasyOCR English allowlist with two-line plate assembly for Vietnamese layouts.

04

Evaluate

evaluate_ocr.py scores cropped plates against labeled text — iterate before you ship gates.

YOLO to OCR pipeline diagram
Pipeline: source frame → YOLOv8 plate box → preprocess → EasyOCR text.

How it works

Three steps from frame to plate string.

Local GPU/CPU for the full Python stack; this host stays a light SaaS shell.

Step 01

Ingest

Camera still, folder batch, or upload in the app shell / HF demo.

Step 02

Localize

YOLO draws the plate ROI; preprocess prepares the crop for OCR.

Step 03

Read & review

EasyOCR returns alnum text; compare with eval or watchlist workflows.

System architecture overview
Architecture overview used in the portfolio case.

Try the demo — no paid GPU claimed here.

Full YOLOv8 + EasyOCR needs a roomy host (not App Service F1). The Azure app runs Tesseract.js in-browser for live plate text; the HF Space mirrors that demo. Source stays in GitHub.

pip install -r requirements.txt
python train.py
python detect.py --source path/to/image.jpg --show
python evaluate_ocr.py

Pricing

Honest free-tier packaging.

No invented paid infra. What you see is what runs on student/free SKUs.

Studio

Free · open source

Clone the repo, train/detect locally, use this landing + app shell on Azure F1.

  • YOLOv8 + EasyOCR scripts
  • Static SaaS UI on plates-ocr
  • HF static browser OCR demo

Ops

Your hardware

Run the Python pipeline on a GPU/CPU box you control — gates, lots, campus cameras.

  • Batch folders & live cam scripts
  • OCR evaluation loop
  • Wire results into your own ACL / parking stack