Facial Expression Recognition
Classify each facial image into one of the seven facial emotion categories considered using CNN based on https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge
Overview:
Facial Expression Recognition is a project that uses Convolutional Neural Networks (CNN) to classify facial images into one of the seven emotional categories. The model was trained and tested on a dataset from the Kaggle Facial Expression Recognition Challenge, containing grayscale images labeled with emotions like anger, disgust, fear, happiness, sadness, surprise, and neutral. By employing Python 2.7, sklearn, numpy, and Keras, the project aims to predict the emotions depicted in facial images.
Features:
- CNN Usage: Utilizes Convolutional Neural Networks for facial expression recognition.
- Data Availability: Dataset includes 35,887 examples with 7 emotion categories.
- Model Variants: Offers both shallow and deep CNN models for classification.
- Evaluation Metrics: Predicts softmax output and uses categorical accuracy for evaluation.
Summary:
Facial Expression Recognition project utilizes Convolutional Neural Networks to classify facial images based on seven emotion categories. By leveraging Python and various libraries, the project provides pre-trained deep CNN models for accurate emotion prediction. With a dataset from Kaggle, the project focuses on achieving high categorial accuracy through model evaluation and experimentation.