ZF/FERPlus
1
0
Fork 0
mirror of https://gitcode.com/gh_mirrors/fe/FERPlus.git synced 2025-12-30 05:22:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update to README.md

Browse Source
This commit is contained in:
Cristian Canton Ferrer
2016-09-21 08:55:12 -07:00
parent 2d321db00f
commit 82f4d35998
1 changed files with 8 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@@ -1,14 +1,17 @@
# FER+
This is new label for Emotion FER dataset. Each image is tagged by 10 crowd-sourced taggers, which provide better quality ground truth for still image emotion than the original FER label. Having 10 taggers for each image enables us to create an emotion probability distribution per face so that we can learn a probability or multi-label instead of the conventional majority voting, as described in: https://arxiv.org/abs/1608.01041
The FER+ annotations provide a set of new labels for the standard Emotion FER dataset. In FER+, each image has been labeled by 10 crowd-sourced taggers, which provide better quality ground truth for still image emotion than the original FER labels. Having 10 taggers for each image enables researchers to estimate an emotion probability distribution per face. This allows constructing algorithms that produce statistical distributions or multi-label outputs instead of the conventional single-label output, as described in: https://arxiv.org/abs/1608.01041
The new label file is named: fer2013new.csv, it contains the same number of rows as the original fer2013.csv label file with the same order, so that you infer which emotion tag belong to which image. Since we can't host the actual image content, please find the original FER data set here: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
Here there is example of the FER vs FER+ labels extracted from the abovementioned paper (FER top, FER+ bottom):
![FER vs FER+ example](https://raw.githubusercontent.com/Microsoft/FERPlus/master/FER+vsFER.png)
We also provide a simple parsing code in python to demonstrate how to parse the new label and how to convert it to probability distribution (there is multiple way to do it, we show an example). The parsing code is in src/ReadFERPlus.py
The new label file is named **_fer2013new.csv_** and contains the same number of rows as the original *fer2013.csv* label file with the same order, so that you infer which emotion tag belong to which image. Since we can't host the actual image content, please find the original FER data set here: https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
The format of the CSV file is as follow: Usage, neutral, happiness, surprise, sadness, anger, disgust, fear, contempt, unknown, NF. Where "Usage" is the same as the original FER label to differentiate between training set, public test set and private test set. The other columns are the vote count for each emotion with the addition of unknown and NF (Not a Face).
We also provide a simple parsing code in Python to show how to parse the new label and how to convert it to a probability distribution (there are multiple ways to do it, we show an example). The parsing code is in [src/ReadFERPlus.py](https://github.com/Microsoft/FERPlus/tree/master/src)
The format of the CSV file is as follow: usage, neutral, happiness, surprise, sadness, anger, disgust, fear, contempt, unknown, NF. Columns "usage" is the same as the original FER label to differentiate between training, public test and private test sets. The other columns are the vote count for each emotion with the addition of unknown and NF (Not a Face).
# Citation
If you use the new FER label or the sample code or part of it in your research, please cite the below:
If you use the new FER+ label or the sample code or part of it in your research, please cite the below:
@inproceedings{BarsoumICMI2016,
    title={Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution},