Processing & Properties of Floor and Wall Tiles.pptx
final ppt -ORIGINAL_Facial_Emotion_Detection special topic -2 review 1-1 (1) (1).pptx
1. DAYANANDA SAGAR UNIVERSITY
SCHOOL OF ENGINEERING
Department of Computer Science and Engineering
Special Topic-II Review 1
<SIMPLE AND MIXED EMOTION IN FACIAL EXPRESSION>
Under the Supervision of
Prof. MONISH.L
(Department of CSE(Data
Science)
Presented By:
MANJUNATH AV
SHAMANTH.K
SHREYAS.S
(ENG20CY0016)
(ENG20CS0328)
(ENG20CS0346)
SHARANESH PRABHU UPASE (ENG21CS1018)
AJITESH.S.KUMAR (ENG20CY0005)
2. OVERVIEW
• ABSTRACT
• PROBLEM STATEMENT
• INTRODUCTION
• IMPORTANCE OF EMOTION RECOGNITION
• LITERATURE SURVEY
• METHODOLOGY
• CNN ALGORITHM
• APPLICATION
• ALGORITHM
• EXPIREMENT & RESULT
• CODE & OUTPUT
• CONCLUSION
• REFERENCES
3. ABSTRACT
• Automatic emotion recognition through facial expression analysis is an
emerging topic on affective computing and social signal processing.
• Existing research on emotion recognition focuses on recognizing basic
emotions (happy, sad, surprise, disgust, fear, and angry), but less effort has
been done for mixed emotion recognition due to its complexity.
• We will identify the simple emotion and the compound emotion in the face and
will compare the emotion of the model.
4. PROBLEM STATEMENT
Identifying the compound emotion is a challenging task. We will
detect the simple emotions like Happy, Sad, so on along with the
compound emotions like Happily surprised, Happily Disgusted in
the face and will try to analyze the person. The objective of both
simple and compound emotion detection to understand the
psychological behavior of the person under observation.
5. INTRODUCTION
• One of the biggest research challenge in intelligent machine is on exploring
human behavior and how they interact with their environment.
• Humans share seven facial expressions that reflect the experiencing of
fundamental emotions. These fundamental, emotions are anger, contempt,
disgust, fear, happiness, sadness, and surprise.
• Computers that can recognize facial expressions can find application where
efficiency and automation can be useful, including in entertainment, social media,
content analysis, criminal justice, and healthcare. For example, content providers
can determine the reactions of a consumer and adjust their future offerings
accordingly.
6. WHAT IS EMOTION?
Emotions are reflected
in voice, hand and
body gestures, and
mainly through facial
expressions
8. IMPORTANCE OF EMOTION RECOGNITION
• Human beings express emotions in day to day
interactions.
• Understanding emotions and knowing how to
react to people’s expressions greatly enriches
the interaction.
9. LITERATURE SURVEY
Author’s
Name/Paper Title
Conference
/journal Name and
year
Techonolo
gy/Design
Result shared by
author
What you
infer
1.Ninad Mehendale
Facial emotion
recognition using
convolutional neural
networks (2020)
SN Applied sciences
2020
Key frame
extraction
from input
video.
Shows regular front-facing
cases with angry and
surprise emotions, and
the algorithm could easily
detect them.
FERC is a novel
way of facial
emotion
detection that
uses the
advantages of
CNN and
supervised
learning
(feasible due to
big data).
2. Dewi Yanti Liliana
Mixed Facial Emotion
Recognition using
Active Appearance
Model and Hidden
Conditional Random
Fields
International Journal of
Pure and Applied
Mathematics Volume
118 No. 18
2018
Mixed Facial
Emotion
Recognition
We test our proposed
AAM HCRF model and
compare it results with
CRF model, and SVM-CRF
model on a modified CK+
dataset as well as our own
made mixed emotion
dataset.
To the best of
our knowledge,
there is no
reporting use of
AAM-HCRF for
mixed
emotion
recognition
previously
10. Author’s
Name/Paper Title
Conference
/journal
Name and
year
Techonology/D
esign
Result shared by
author
What you
infer
3. Illiana Azizan
Facial Emotion
Recognition
International
Conference Of
Sustainable
Engineering ,
Technology
and
Management
(ICSETM-2018)
Dec 20, 2018
Local Binary
Pattern, Linear
Discriminant
Analaysis.
Emotion expression is
important in
communication, hence
improving the quality of
interaction between
human. The study of
facial emotion
recognition between
Human Robot Interface
(HRI) in a near future.
HMM use a set of
statistical model
to describe the
statistical
behaviour of a
signal and SVM
used different
kernel function to
map data in input
space into high
dimensional
feature spaces
4. Zhihan Lv
Emotion Recognition of
Students Based on
Facial Expressions in
Online Education Based
on the Perspective of
Computer Simulation
Complexity,
vol. (2020)
In addition to the
vision-based
methods, other
biometric
techniques can
also be adopted.
the result of this
experiment can provide
favorable support for the
performance of the
model when applied to
real environment.
By inputting this
image into the
applied CNN
model, we
obtained the
emotional tags
11. PROPOSED METHODOLOGY
• Capture images
• Image pre-processing
i. RGB to grey scale conversion
ii. Scale-Normalization
• Feature Recognition
• Building the model
• Training
• Simple and compound Facial
Emotion Recognition
• Measuring the performance of the
model
13. CONVOLUTION NEURAL NETWORK
ALGORITHM (CNN)
Convolutional Neural Network (CNN) is an neural network which extracts or
identifies a feature in a particular image. This forms one of the most
fundamental operations in Machine Learning and is widely used as a base
model in majority of Neural Networks like GoogleNet, VGG19 and others for
various tasks such as Object Detection, Image Classification and others.
CNN has the following five basic components:
•Convolution : to detect features in an image.
•ReLU : to make the image smooth and
make boundaries distinct.
•Pooling : to help fix distored images.
•Flattening : to turn the image into a
suitable representation.
•Full connection : to process the data in a
• neural network.
15. ALGORITHM
Step 1: Take a still image of a normal expression pic1 (say) of a human face.
Step 2: Converts the color image to grayscale.
Step 3: Crop the five facial image region of interest (ROI) (eyes, eye brows and lip)
from the image by defining region.
Step 4: Find edges of all image region.
Step 5: Take a still image of a emotional face (angry or happy) pic2 (say) of same
person and repeat step 2, 3 and 4.
Step 7: Comparing the deviation of edges of the specified region of pic1 with
pic2 by finding the Euclidian distances of coordinate of each pixel.
Step 8: Put the Euclidian distances in a array k (say).
Step 9: Find the standard deviation (SD)fromtheelements of array.
Step 10: Comparing the SD with pre-define thresholdand get the emotions.
16. Experiment & Result
30 images were used to create the template.
60 were tested.
Statistical Values of Three categories
18. Conclusion
o Implementation through this process is quite easy.
o Have to improve over the capturing Process.
o Edge detection procedure should be less complex.
19. REFERENCES
• W.Swinkels, L. Claesen , F.Xiao and H. Shen, "SVM point-based real-time emotion
•detection," 2017 IEEE Conference on Dependable and Secure Computing, Taipei,
•2017.
• A. C. Le Ngo, Y
.H. Oh, R. C. W.Phan and J. See, "Eulerian emotion magnification
for subtle expression recognition," 2016 IEEE International Conference on
Acoustics, Speech and Signal Processing (ICASSP), Shanghai, 2016
• V. Kazemi and J. Sullivan, "One millisecond face alignment with an ensemble
of regression trees," 2014 IEEE Conference on Computer Vision and Pattern
Recognition, Columbus, OH, 2014
• G. T.Kaya, "A Hybrid Model for Classification of Remote Sensing Images With
Linear SVM and Support Vector Selection and Adaptation," in IEEE Journal of
Selected Topics in Applied Earth Observations and Remote Sensing, vol. 6, no. 4, pp.
1988-1997, Aug. 2013
• J. J. Lee, M. Zia Uddin and T.S. Kim, "spatiotemporal human facial
expression recognition using fisher independent component analysis and
Hidden Markov Model," 2008 30th Annual International Conference of the
IEEE Engineering in Medicine and Biology Society, Vancouver, BC, 2008.