Added Number plate detection project

Number-Plate-Detection/Numberplatedetection.py

@@ -0,0 +1,67 @@
+import cv2
+import os
+import time
+
+cascade_path = 'indian_license_plate.xml'
+plate_cascade = cv2.CascadeClassifier(cascade_path)
+if plate_cascade.empty():
+    print(f"Error loading cascade from {cascade_path}")
+    exit()
+
+os.makedirs('plates', exist_ok=True)
+video_path = 'Trafic Camera.mp4'
+cap = cv2.VideoCapture(video_path)
+if not cap.isOpened():
+    print(f"Error opening video file {video_path}")
+    exit()
+
+plate_count = 0
+last_save_time = 0
+save_delay = 0.5
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        print("End of video or cannot read frame.")
+        break
+
+    frame = cv2.resize(frame, (960, 540))
+
+    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+
+    gray = cv2.equalizeHist(gray)
+
+    gray = cv2.bilateralFilter(gray, 11, 17, 17)
+
+    roi = gray[270:540, :]
+
+    plates = plate_cascade.detectMultiScale(
+        roi,
+        scaleFactor=1.05,
+        minNeighbors=7,
+        minSize=(60, 20)
+    )
+
+    current_time = time.time()
+
+    for (x, y, w, h) in plates:
+        y += 270
+
+        aspect_ratio = w / h
+        if 2 < aspect_ratio < 5:
+            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
+
+            if current_time - last_save_time > save_delay:
+                plate_count += 1
+                plate_img = frame[y:y+h, x:x+w]
+                cv2.imwrite(f"plates/plate_{plate_count}.jpg", plate_img)
+                print(f"Saved plate_{plate_count}.jpg")
+                last_save_time = current_time
+
+    cv2.imshow("Number Plate Detection", frame)
+
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        print("Quit pressed, exiting.")
+        break
+cap.release()
+cv2.destroyAllWindows()

Number-Plate-Detection/README.md

@@ -0,0 +1,88 @@
+# Number Plate Detection 🚘🔍
+
+This project is a simple Number Plate Detection system built using **OpenCV** and **Python**. It uses image processing techniques and a pre-trained Haar Cascade classifier to detect number plates in real-time from video streams or static images.
+
+## 📸 Demo
+
+![Screenshot 2025-05-21 160620](https://github.com/user-attachments/assets/fd6d233e-a948-4015-aab3-50ec09ac9f75)
+
+
+## 🧠 Features
+
+- Real-time number plate detection using webcam
+- Uses OpenCV's Haar Cascade Classifier
+- Highlights detected number plates with rectangles
+- Can be extended for OCR (Optical Character Recognition)
+
+## 🛠️ Technologies Used
+
+- Python 3.x
+- OpenCV
+- Haar Cascade Classifier
+
+## 📁 Project Structure
+
+Number-Plate-Detection/
+
+│
+
+├── Numberplatedetection.py # Main script for plate detection
+
+├── haarcascade_russian_plate_number.xml # Haar Cascade model for number plates
+
+└── README.md # Project documentation
+
+## 🚀 How to Run
+
+### 1. Clone the Repository
+
+```bash
+git clone https://github.com/iamdevdhanush/Number-Plate-Detection.git
+cd Number-Plate-Detection
+```
+
+2. Install Requirements
+
+```bash
+pip install opencv-python
+```
+
+3. Run the Script
+
+```bash
+python Numberplatedetection.py
+```
+
+📦 Dependencies
+```
+opencv-python
+```
+You can install them using pip:
+
+```
+pip install -r requirements.txt
+```
+
+📌 Notes
+
+Make sure you have the correct Haar Cascade XML file (haarcascade_russian_plate_number.xml).
+
+This project is a basic implementation and doesn't perform OCR. You can extend it using pytesseract for extracting plate text.
+
+🤖 Future Improvements
+
+Add OCR to extract text from number plates
+
+Improve accuracy with deep learning-based detection (YOLO, SSD)
+
+Support detection in images and video files
+
+📄 License
+
+This project is licensed under the MIT License.
+
+🙋‍♂️ Author
+
+Dhanush
+
+GitHub