A web-based application that detects and blurs faces in images, built using YOLO v8 and HaarCascade Classifier detection algorithms with Streamlit.
Blurify.AI is a web-based application that allows you to upload an image and detect and blur all faces within that image. The project was built using the YOLO v8 and HaarCascade Classifier object detection algorithms and Streamlit framework. The application can be used to anonymize faces in images, preserving privacy and confidentiality. It can also be used for creative purposes such as adding a blur effect to a portrait.
Blurify.AI was built using the YOLO v8 and HaarCascade Classifier object detection algorithms and Streamlit web framework. The YOLO v8 algorithm is a state-of-the-art object detection algorithm that is highly accurate and efficient. Streamlit is a popular web framework that allows you to quickly build and deploy web-based applications using Python. The project was trained on a dataset of faces to detect and blur faces in images uploaded by the user.
Ckech the GitHub repo for building the models, evaluations, etc. the link
To deploy Blurify.AI locally, follow the steps below:
- Clone the repository by running the following command:
git clone https://github.com/baselhusam/Blurify.AI.gi
- Navigate to the project directory and install the required packages by running the following command:
pip install -r requirements.txt
- Start the application by running the following command:
streamlit run main.py
- Open your browser and go to
http://localhost:8501/
to use the application locally.
Using Blurify.AI is simple and easy. Simply follow the steps below:
-
Deploy the web-app locally with the previous steps.
-
Click on the "Upload Image" button and select an image from your device.
-
Click on the "Blurify" button.
-
Wait for the algorithm to detect and blur faces in the image.
-
Download the blurred image by right click and select "Save image as".
That's it! Your image is now blurred and ready to use.
how_to_use_video.mp4
This project is licensed under the MIT License - see the LICENSE file for details.
This project was built with ❤️ by Basel Husam.