Emotion Recognition is a cutting-edge deep learning project designed to detect and classify human emotions based on facial expressions. Using a Convolutional Neural Network (CNN), the model is trained on the FER2013 dataset and can accurately recognize seven distinct emotions

A deep learning-based system that detects facial expressions from webcam input and classifies them into seven emotions — Angry, Disgust, Fear, Happy, Neutral, Sad, and Surprise — using a CNN model and OpenCV for real-time face detection.

Emotion detection typically categorizes emotions into basic or complex categories such as happiness, sadness, anger, fear, surprise, disgust, and sometimes more nuanced emotions like confusion, excitement, or trust. These categories can vary depending on the specific application and dataset.

Emotion Detector app to detect realtime facial expression using Kotlin.

This pipeline was created as part of a 7.5 ECTS research project during the MSc in Software Design program at the IT University of Copenhagen. It is an EEG data preprocessing tool designed to support newcomers in preprocessing of EEG data. The pipeline outputs a cleaned EEG file in .fif format along with a detailed report.

A real-time facial emotion recognition system that syncs music from Spotify or local files to match your mood using DeepFace and OpenCV.

A web-based platform for proactive mental health management. Analyzes daily text/audio inputs to detect emotional states using ML + NLP, and delivers personalized book, movie, song, and activity recommendations. Tracks weekly emotional trends and progress with insightful reports. Built with the MERN stack & Flask.