Scribd
Upload
11 views5 pages

Emotion Recognition with FER2013 Dataset

This document outlines a mid-term project to perform emotion recognition using deep learning and the Kaggle FER2013 dataset. The dataset contains facial images labeled with 7 emotion classes. A convolutional neural network architecture will be used to classify images into these 7 emotions. Various techniques will be explored to improve the model performance, such as convolutional layer design, data augmentation, and activation functions. Results from experiments will be analyzed and reported.

Uploaded by

nghitran.31221020434
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
11 views5 pages

Emotion Recognition with FER2013 Dataset

This document outlines a mid-term project to perform emotion recognition using deep learning and the Kaggle FER2013 dataset. The dataset contains facial images labeled with 7 emotion classes. A convolutional neural network architecture will be used to classify images into these 7 emotions. Various techniques will be explored to improve the model performance, such as convolutional layer design, data augmentation, and activation functions. Results from experiments will be analyzed and reported.

Uploaded by

nghitran.31221020434
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd

Mid-Term Project

Emotion Recognition using Deep


Learning
2

The Dataset(1)
• Kaggle FER2013 Dataset
• Facial Expression Recognition Challenge
• 7 classes: (0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise,
6=Neutral)
3

The Dataset(2)
• Train & Testing Data
• [Link]
pression-recognition-challenge/data
• [Link]
• World-best accuracy: 69%(public), 71%(private)
4

CNN Architecture
• Input/Output & Environment
• Input: 48x48 image
• Output: 7D vector  emotion classes
• Performance Improvements
• CNN model design(Conv, MaxPooling, Dropuout, FC, …)
• Training techniques: optimization algorithm, data augmentation, …
• Activation function: ReLU, sigmoid, …
Pay Attention
• Refer to the sample code
• Submission
• Report
• Brief summary for source codes
• Results for many experiments with various parameter settings
• Visualize the final convolution filters
• Analysis and explanation about the results in your own way
• Python Source Code using Keras

You might also like