This project demonstrates object detection using the Ultralytics YOLO models (yolo11n.pt and yolo11s.pt). It includes:

• A Jupyter Notebook/Google Colab for experimenting with YOLO detection.
• Streamlit apps for detecting objects in images and videos.
• A Webcam script for real-time detection.

• Detect objects in:

  • Single Image
  • Multiple Images
  • Image or Video
  • Live Webcam Stream

• Real-time bounding boxes, labels, and confidence scores.

• Class-wise detection summary.

• Streamlit apps for interactive browser usage.

├── performingObjectDetectionUsingYOLO11n.ipynb   # Notebook version
├── objectDetectionSoloImg.py                     # Streamlit app: single image
├── objectDetectionMultipleImg.py                 # Streamlit app: multiple images
├── objectDetectionSoloImgVid.py                  # Streamlit app: image or video
├── useCamToFind.py                               # Live webcam detection
├── requirements.txt                              # Dependencies
├── README.md                                     # Project documentation
└── runs/                                         # YOLO outputs (auto-created)

1. Clone this repository:

   git clone https://github.com/arupa444/OCR-Using-YOLO.git
   cd OCR-Using-YOLO

2. Create a virtual environment:

   python -m venv .venv
   source .venv/bin/activate   # Mac/Linux
   .venv\Scripts\activate      # Windows

3. Install dependencies:

   pip install -r requirements.txt

jupyter notebook performingObjectDetectionUsingYOLO11n.ipynb

Inside the notebook:

!yolo predict model=yolo11n.pt source='image.jpg'

!yolo predict model=yolo11n.pt source='video.mp4'

!yolo predict model=yolo11n.pt source=0

streamlit run objectDetectionSoloImg.py

streamlit run objectDetectionMultipleImg.py

streamlit run objectDetectionSoloImgVid.py

python useCamToFind.py

• Uses your default webcam (source=1).
• Opens a live window with bounding boxes.
• Saves detection results in runs/detect/.

• Annotated images/videos are shown directly in the apps.

• YOLO saves all processed results inside:

  runs/detect/
  

  Each execution creates a new timestamped folder.

• Python 3.8+
• Jupyter Notebook/Google Colab
• Ultralytics YOLO
• Streamlit
• Pillow
• NumPy
• OpenCV
• Torch + TorchVision

Install directly with:

pip install ultralytics streamlit pillow numpy opencv-python torch torchvision

from ultralytics import YOLO

model = YOLO("yolo11n.pt")
results = model("image.jpg")
results.show()

This project is licensed under the MIT License. Feel free to use and modify.