Neural network to facial expression recognition
Clone or download
Pull request Compare This branch is 6 commits ahead of NunoRamos:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
GFEData
Parser
Reports
Results
experiment1
experiment2
experiment3
experiment4
.gitignore
README.md
app-screenshot.png

README.md

IART-FEUP - Neural network to rate facial expressions.

Live App

Contributors

  1. Maria João Mira Paulo
  2. Nuno Miguel Mendes Ramos
  3. Pedro Duarte da Costa

Index

  1. Introduction
  2. Resources
  3. Project Structure

Introduction

In this project, we are going to implement a neural network for recognizing Grammatical Facial Expressions (GFEs) used in the Brazilian Sign Language. To do so we'll use ConvNetJS, a Javascript library, to train a neural network using backpropagation algorithms.

Live App

Final Report

Resources

Project Structure

GFE Data

Pre-processed

JSON formated pre-processed data can be found in the folder JSON inside each experiment.

Processed points

Raw

Grammatical Facial Expressions for Brazilian Sign Language

The dataset is organized in 36 files: 18 datapoint files and 18 target files, one pair for each video which compose the dataset.The name of the file refers to each video: the letter corresponding to the user (A and B), name of grammatical facial expression and a specification (target or datapoints).

Contains:

  • Datapoints files (* _ datapoints.txt): a timestamp (double) and 100 numeric attributes (double)

  • Targets files (* _ targets.txt): a class attribute (interger)

Parser

Small CLI python program to parse datapoints in a .txt files to usefull data in .json format

Reports

Project reports.

Experiment1: Default experiment

Experiment2: Increased number of datapoints

Experiment3: Reducted number of given neutral expressions

Experiment4: Tested a neural expression for each expression

WebApp Screenshot

App Screenshot