Emotion Recognition through CNN is a deep learning model that detects seven facial emotions using a custom ConvNet. It combines features from LBP, ORB, and CNN, achieving up to 98.13% accuracy on JAFFE and 91.01% on FER2013. The model supports real-time emotion detection and is publicly available for research use. Trained with TensorFlow.
☆27Apr 2, 2026Updated 5 months ago
Alternatives and similar repositories for Emotion-recognition-through-CNN
Users that are interested in Emotion-recognition-through-CNN are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- a TensorFlow implementation of the paper "Feature Super-Resolution Based Facial Expression Recognition for Multi-scale Low-Resolution Ima…☆13Nov 30, 2021Updated 4 years ago
- Repository for ACL2020 paper "Refer360° A Referring Expression Recognition Dataset in 360°Images"☆15Jun 26, 2021Updated 5 years ago
- ☆11Aug 13, 2023Updated 3 years ago
- The code for "EEG-based Emotion Recognition Using Convolutional Neural Network with Functional Connections"