Automatic Analysis of Facial Expressions: The State of the Art Maja ...

brasscoffeeIA et Robotique

17 nov. 2013 (il y a 5 années et 6 mois)

631 vue(s)

Automatic Analysis of Facial

The State of the Art

By Maja Pantic, Leon Rothkrantz

Presentation Outline


Desired functionality and evaluation criteria

Face Detection

Expression data extraction


Conclusions and future research



Hope to achieve robust communication by recovering from
failure of one communication channel using information
from another channel

According to some estimates, the facial expression of the
speaker counts for 55% of the effect of the spoken message
(with the voice intonation contributing 38%, and the verbal
part just 7%)

Behavioral science research

Automation of objective measurement of facial activity

Desired Functionality

Human visual system = good reference point

Desired properties:

Works on images of people of any sex, age, and ethnicity

Robust to variation in lighting

Insensitive to hair style changes, presence of glasses, facial
hair, partial occlusions

Can deal with rigid head motions

Is real

Capable of classifying expressions into multiple emotion

Able to learn the range of emotional expression by a particular

Able to distinguish all possible facial expressions (probably


Three basic problems need to be solved:

Face detection

Facial expression data extraction

Facial expression classification

Both static images and image sequences have
been used in studies surveyed in the paper

Face Detection

In arbitrary images

A. Pentland et al.

Detection in a single image

Principal Component Analysis is used to generate a face space
from a set of sample images

A face map is created by calculating the distance between the local
subimage and the face space at every location in the image

If the distance is smaller than a certain threshold, the presence of a
face is declared

Detection in an image sequence

Frame differencing is used

The difference image is thresholded to obtain motion blobs

Blobs are tracked and analyzed over time to determine if motion is
caused by a person and to determine the head position

Face Detection (Continued)

In face images

Holistic approaches (the face is detected as a whole unit)

M. Pantic, L. Rothkrantz

Use a frontal and a profile face images

Outer head boundaries are determined by analyzing the horizontal and
vertical histograms of the frontal face image

The face contour is obtained by using an HSV color model based
algorithm (the face is extracted as the biggest object in the scene having
the Hue parameter in the defined range)

The profile contour is determined by following the procedure below:

The value component of the HSV color model is used to threshold the
input image

The number of background pixels between the right edge of the image and
the first “On” pixel is counted (this gives a vector that represents a discrete
approximation of the contour curve)

Noise is removed by averaging

Local extrema correspond to points of interest (found by determining zero
crossings of the 1st derivative)

Face Detection (Continued)

Analytic approaches (the face is detected by
detecting some important facial features first)

H. Kobayashi, F. Hara

Brightness distribution data of the human face is obtained with
a camera in monochrome mode

An average of brightness distribution data obtained from 10
subjects is calculated

Irises are identified by computing crosscorrelation between the
average image and the novel image

The locations of other features are determined using relative
locations of the facial features in the face

based facial expression
data extraction using static images

Edwards et al.

Use Active Appearance Models (AAMs)

Combined model of shape and gray
level appearance

A training set of hand
labeled images with landmark
points marked at key positions to outline the main

PCA is applied to shape and gray level data separately,
then applied again to a vector of concatenated shape and
gray level parameters

The result is a description in terms of “appearance”

80 appearance parameters sufficient to explain 98% of
the variation in the 400 training images labeled with 122

Given a new face image, they find appearance parameter
values that minimize the error between the new image
and the synthesized AAM image

based facial expression data
extraction using static images

M. Pantic, L. Rothkrantz

A point
based face model is used

19 points selected in the frontal
view image, and 10 in the
view image

Face model features are defined as some geometric
relationship between facial points or the image intensity
in a small region defined relative to facial points (e.g.
Feature 17 = Distance KL)

Neutral facial expression analyzed first

The positions of facial points are determined by using
information from feature detectors

Multiple feature detectors are used for each facial feature
localization and model feature extraction

The result obtained from each detector is stored in a
separate file

The detector output is checked for accuracy

After “inaccurate” results are discarded, those that were
obtained by the highest priority detector are selected for
use in the classification stage

based facial expression
data extraction using image

M. Black, Y. Yacoob

Do not address the problem of initially locating the
various facial features

The motion of various face regions is estimated
using parameterized optical flow

Estimates of deformation and motion parameters
(e.g. horizontal and vertical translation, divergence,
curl) are derived

based facial expression data
extraction using image sequences

Cohn et al. (the only surveyed method)

Feature points in the first frame manually marked with a
mouse around facial landmarks

A 13x13 flow window is centered around each point

Hierarchical optical flow method of Lucas and Kanade used
to track feature points in the image sequence

Displacement of each point calculated relative to the first

The displacement of feature points between the initial and
peak frames used for classification


Two basic problems:

Defining a set of categories/classes

Choosing a classification mechanism

People are not very good at it either

In one study, a trained observer could classify only 87% of the faces

Expressions can be classified in terms of facial actions that cause
an expression or “typical” emotions

Facial muscle activity can be described by a set of codes

The codes are called Action Units (AUs). All possible, visually detectable
facial changes can be described by a set of 44 AUs. These codes form the
basis of Facial Action Coding System (FACS), which provides a linguistic
description for each code.

Classification (continued)

Most of the studies perform an
emotion classification and use the
following 6 basic categories:
happiness, sadness, surprise, fear,
anger, and disgust

No agreement among psychologists
whether these are the right

People rarely produce “pure”
expressions (e.g. 100% happiness),
blends are much more common

based classification using
static images

Edwards et al.

The Mahalanobis distance measure can be used for classification

Classification into 6 basic + neutral categories

Correct recognition of 74% reported

c is the vector of appearance parameters for the new image,

is the centroid of the multivariate distribution for class i, and C

is the within
class covariance matrix for all the training images

Neural network
based classification
using static images

H. Kobayashi, F. Hara

Used 234x50x6 neural network trained off
line using

The input layer units correspond to intensity values extracted
from the input image along the 13 vertical lines

The output units correspond to the 6 basic emotion

Average correct recognition rate 85%

Neural network
based classification
using static images (Continued)

Zhang et al.

Used 680x7x7 neural network

Output units represent six basic emotion categories plus the
neutral category

Output units give a probability of the analyzed expression
belonging to the corresponding emotion category

validation used for testing

J. Zhao, G. Kearney

Used 10x10X3 neural network

Neural network trained and tested on the whole set of data
with 100% percent recognition rate

based classification using static

M. Pantic, L. Rothkrantz (the only surveyed method)

stage classification:

1. Facial actions (corresponding to one of the Action Units) are deduced from
changes in face geometry

Action Units are described in terms of face model feature values (E.g. AU 28 = (Both)
lips sucked in = feature 17 is 0, where feature 17 = Distance KL)

2. The stage 1 classification results are used to classify the expression into one of
the emotion categories

E.g. AU6 + AU12 + AU16 + AU25 => Happiness

The two
stage classification process allows “weighted emotion labels”

Assumption: each AU that is part of the AU
coded description of a “pure”
emotional expression has the same influence on the intensity of that emotional

E.g. If the analysis of some image results in the activation of AU6, AU12, and
AU16, then the expression is classified as 75% happiness

The system can distinguish 29 AUs

Recognition rate 92% for upper face Aus, and 86% for lower face AUs

based classification using
image sequences

Cohn et al.

Classification in terms of Action Units

Uses Discriminant Function Analysis

Deals with each face region separately

Used for classification only (i.e. all facial point
displacements are used as input)

Does not deal with image sequences containing
several consecutive facial actions

Recognition rate: 92% in the brow region, 88% in
the eye region, 83% in the nose and mouth region

based classification

using image sequences

M. Black, Y. Yacoob (the only surveyed method)


and high
level descriptions of facial actions are used

The parameter values (e.g. translation, divergence) derived from
optical flow are thresholded

E.g. Div >0.02 => expansion, Div <
0.02 => contraction. This is what
the authors would call a mid
level predicate for the mouth.

level predicates are rules for classifying facial expressions

Rules for detecting the beginning and the end of an expression

Use the results of applying mid
level rules as input

E.g. Beginning of surprise = Raising brows and vertical expansion of
mouth, End of Surprise = Lowering brows and vertical contraction of

The rules used for classification are not designed to deal with
blends of emotional expressions (Anger + Fear recognized as

Recognition rate: 88%

Conclusions and Possible Directions
for Future Research

Active research area

Most surveyed systems rely on the frontal view of the face and
assume no facial hair or glasses

None of the surveyed systems can distinguish all 44 AUs defined

Classification into basic emotion categories in most surveyed

Some reported results are of little practical value

The ability of the human visual system to “fill in” missing parts
of the observed face (i.e. deal with partial occlusions) has not
been investigated

Conclusions and Possible Directions
for Future Research (Continued)

Not clear at all whether the 6 “basic” emotion categories are

Each person has his/her own range of expression intensity

systems that start with a generic classification and then adapt
may be of interest

Assignment of a higher priority to upper face features by the
human visual system (when interpreting facial expressions) has
not been subject of a lot of research

Hard or impossible to compare reported results objectively
without a well
defined, commonly used database of face images


M. Pantic, L. Rothkrantz, “Automatic Analysis of Facial Expressions: The State of the
Art”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No.
12, December 2000

M. Pantic, L. Rothkrantz, Expert System for Automatic Analysis of Facial
Expressions, Image and Vision Computing, Vol. 18, No. 11, pp. 881
905, 2000

M. J. Black, Y. Yacoob, “Recognizing Facial Expressions in Image Sequences Using
Local Parameterized Models of Image Motion”, Int’l J. Computer Vision, Vol. 25, no.1,
pp. 23
48, 1997

J. F. Cohn, A.J. Zlochower, J.J. Lien, T. Kanade, “Feature
Point Tracking by Optical
Flow Discriminates Subtle Differences in Facial Expression”, Proc. Int’l Conf.
Automatic Face and Gesture Recognition, pp. 396
401, 1998

G.J. Edwards, T.F. Cootes, C.J. Taylor, “Face Recognition Using Active Appearance
Models”, Proc. European Conference on Computer Vision, Vol. 2, pp. 581
695, 1998

G.J. Edwards, T.F. Cootes, C.J. Taylor, “Active Appearance Models”, Proc. European
Conf. Computer Vision, Vol. 2, pp. 484
498, 1998

H. Kobayashi, F. Hara, “Facial Interaction between Animated 3D Face Robot and
Human Beings”, Proc. Int’l Conf. Systems, Man, Cybernetics, pp.3,732
3,737, 1997

Some YouTube Videos

time facial expression recognition

Take 2

Facial expression recognition

Facial expression mirroring

Facial expression animation