This project, developed with VS Code and Google Colab, uses Python (Flask, Facenet/Pytorch, FAISS Index) and Postman (for API Testing) to return the most similar picture of a person, when the input is a picture of a person whose picture is present in the LFW (Labelled Faces in the Wild) dataset (available on Kaggle).
Potential improvements that I want to implement:
- Using a Vector DB, like Milvus
- Using libraries like Deepface
- Handling multiple persons in an image
- Adding more information for better face matching!
Thanks to Akshay sir, Abhishek sir, Balesh sir, and Mayank for the constant guidance and support.
Thanks to Cubastion Consulting Pvt. Ltd. for a productive and supportive environment that fosters learning.