/Perform-automatic-image-indexing

Classical approach vs cnn approach to detect the dog' breed from his image.

Primary LanguageJupyter Notebook

centrale logo

animal protection association: Perform automatic image indexing

This project intends to provide a python application , which allow to animals protection association to detect dogs' breed based on their images provided by their owners. We had tested two approaches : classical approach with features extractions, bags of visual words and traditional machine learning classifiers. Modern approach, wich consist to use cnn and transfer learning.

Built With 🔨

  • Python
  • Scikit-Learn
  • Deep learning
  • Keras
  • transfer learning (vgg16)
  • openCV
  • SIFT features extractors

Project presentation

Live Demo Link

Install

To get a local copy up and running follow these simple example steps.

  • Open terminal
  • Clone this project by the command:
$ git clone git@github.com:Taher-web-dev/Perform-automatic-image-indexing.git
  • Then go to the main folder using the next command:
$ cd Perform-automatic-image-indexing

Prerequisites

  • IDE to edit and run the code (We use Jupyter Notebook 🔥).
  • Git to versionning your work.

Usage

  • Data scientist practioner
  • For anyone interested by computer vision topics.

Authors

👤 Taher Haggui

🤝 Contributing

Contributions, issues, and feature requests are welcome!

Show your support

Give a ⭐️ if you like this project!

Acknowledgments

📝 License

This project is Openclassroom licensed.