Emojify

The objective of this machine learning project is to classify human facial expressions and map them to emojis using CNN.

This is basically a learning project for me. Thanks to Data Flair .

With advancements in computer vision and deep learning, it is now possible to detect human emotions from images. This project classifies human facial expressions to filter and map corresponding emojis or avatars.

Dataset

The FER2013 dataset ( facial expression recognition) consists of 48*48 pixel grayscale face images. The images are centered and occupy an equal amount of space. This dataset consist of facial emotions of following categories

0. angry
1. disgust
2. fear
3. happy
4. sad
5. surprise
6. neutral

---

Steps

1. Download and Extract dataset in 'data' folder with separate 'train' and 'test' directories.
2. Install required libraries mentioned in both '.py' files.
3. Donwload 'emojis' folder from repository and paste in your project directory where you have your '.py' files.
4. Run 'train.py' file. It will take time, depending on your system. Complete this step without interruption. This is for training of your model without which it won't be able to classify emotions accurately.
5. After successfull execution of 'train.py' file, run 'gui.py' file to check the working of your model.

Have a fun!

All © Copyrights for any content of this repository belong to their respective owners.