PERFORMANCE EVALUATION AND IMPLEMENTATION OF FACIAL EXPRESSION AND EMOTION RECOGNITION SYSTEM USING PRINCIPAL COMPONENT ANALYSIS
1. A Synopsis of the proposed research plan submitted for
the degree of
Master of Technology
in
Computer Science and Engineering
PRESENTED BY:-
AKHIL UPADHYAY
M-TECH 3rd SEM CSE
ROLL NO.- 121140002
GUIDED BY:-
MR. ROHIT MIRI
H.O.D. OF COMPUTER
SCIENCE DEPARTMENT
2.
3. 1.INTRODUCTION
Human correspondence has two primary viewpoints:
Verbal (sound-related)
Non-verbal (visual)
Facial Expression is the most important mode of non-verbal
communication between people.
Facial expression carries crucial information
about the mental, emotional and even physical states of the
conversation.
(Cont..)
4. The human face is an elastic object that consists of organs,
numerous muscles, skins, and bones. When a muscle contracts,
the transformation of the corresponding skin area attached to
the muscle result in a certain type of visual effect.
Facial expression is one of the most powerful, natural, and
immediate means for human beings to communicate their
emotions and intentions.
The face can express emotion sooner
than people verbalize or even realize their feelings.
The contours of the mouth, eyes and
eyebrows play an important role in classification.
(Cont..)
5. HUMAN EMOTIONS
Humans are filed with numerous type of expression and
emotions. But the universal categories of emotions are
happiness, sadness, surprise, fear, anger, and disgust.
6. Happiness
The power of an upbeat expression is basically dictated by
the lip position. The mouth might possibly be pated, with
teeth uncovered or not. Furthermore, a glad individual
shows wrinkle lines running from the nose out and down to
the range past the edges of the mouth.
7. Anger
The eyebrows are brought down are brought down, and
drawn together, the eyelids are tensed, and drawn together,
the eyelids are tensed, and the eye seems to gaze in hard
manner. The lips are either firmly squeezed together or
opened in a square.
8. Surprise
broadening of the eyes, brief suspension of breathing, and
general loss of muscle tone. The loss of muscle tone causes the
mouth to fall open, and may make the subject amaze or compel
him to take a seat. Practically anything can be astounding; a
sight, smell, taste, touch and definitely, the more prominent the
unforeseen thing, the more amazed you will be.
9. Disgust
The presence of full-face revulsion is portrayed as; the upper top is
raised, the lower lip is raised and pushed up to the upper lip, or is
brought down and the nose is wrinkled, the cheeks are raised, lines
show beneath the lower top pushed up however not strained, the
forehead is brought down, bringing down the upper top.
10. Fear
The presence of full-face apprehension is portrayed as; the eyebrows
are raised and drawn together, the eyes are open, and the lower
cover is tensed, and lips are extended back dissimilar to in
astonishment look.
11. Sadness
The internal corners of the eyebrows are drawn up and the upper
eyelid is raised and the edge of the lips are down. Misery mixes with
trepidation and outrage generally.
12. LITERATURE REVIEW
A Robust Face Detection Method Based on Skin Color and Edges
Deepak Ghimire et al. (2013) Face detection is concerned with
finding whether or not a face exists in a given image; if face is
present, it returns the image location and face size.
The advance of computer technology in recent years has
facilitated the development of real-time vision modules that
can interact with humans.
Facial Expression Recognition using Neural Network
Pushpaja V. Saudagare et al. (2012) in many face recognition
systems the important part is face detection. Classification of
face detection and token matching can be carried out any
neural network for recognizing the facial expression
13. OBJECTIVE
Facial expression recognition system has turn into a most
emphasizing research area since it plays a most important part in
human-computer-interaction.
The face can articulate emotion sooner than people verbalize
or even understand their posture.
This synopsis report describes Integrated System for Facial
Expression Recognition (ISFER), which performs facial
expression analysis from a still dual facial view image.
Modeling the facial emotion and its intensity.
14. METHODOLOGY
Principal Component Analysis (PCA) is a classical feature
extraction and data representation technique widely used in the
area of pattern recognition and Computer Vision.
The Purpose of PCA is to reduce the large dimensionality data
space into the smaller dimensionality feature space need to
describe the data economically
The main idea of PCA is to find the vectors which best
accounts for the distributions of face images within the entire
image space.
15. PROPOSED WORK
Image Acquisition
Preprocessing
Segmentation
Extraction
Classification
Fig: Face recognition system can be formulated as following phases
Image Acquisition :
Images used for facial expression
recognition are still images or image
sequence.
Two Dimensional facial images are used
Two Dimensional human facial images
pixel and intensities are used as input
dataset
16. PROPOSED WORK
Image Acquisition
Preprocessing
Segmentation
Extraction
Classification
Fig: Face recognition system can be formulated as following phases
Preprocessing :
Preprocessing of acquired image is
important step to get efficient result.
It includes noise removal, and
normalization against the variation of pixel
position or brightness.
PCA technique is used for normalization
and resizing of image pixel in N*N Matrix
17. PROPOSED WORK
Image Acquisition
Preprocessing
Segmentation
Feature Extraction
Classification
Fig: Face recognition system can be formulated as following phases
Segmentation :
Segmentation is concerned with the
demarcation
of image portions conveying relevant facial
information
shape , motion, color, texture, and spatial
configuration of the face or its Components.
Covariance Matrix of dimensions N2*N2
to determine eigen vectores and eigen values.
18. PROPOSED WORK
Image Acquisition
Preprocessing
Segmentation
Feature Extraction
Classification
Fig: Face recognition system can be formulated as following phases
Classification :
Classification technique is used to classify
image category.
In this Eigen vectors are compared with
the training set to classify the image of
different moods.
This is the last process to get desired
output.
19. Application
With facial expression recognition systems, the computer will
be able to
assess the human expressions depending on their effective state in
the same way that human’s senses do
Facial expression recognition has practical significance; it has
very broad application prospects, such as user-friendly interface
between man and machine, humanistic design of goods, and
emotional robot etc
20. The facial expression recognition system has been used in
communication to make the answer machine more
interactive with people
the facial expression recognition system has been used in
communication to make the answer machine more
interactive with people
The facial expression recognition system applied in
different areas of life such as security and surveillance, they
can predict the offender or criminal’s behavior by analyzing
the images of their faces that are captured by the control-
camcorder.
21. EXPECTED OUTCOMES
There has been continued research interest in enabling
computer systems to recognize expressions and to use the emotive
information embedded in them in human-machine interfaces.
This paper presents a high-level overview of automatic
expression recognition; it highlights the main system components
and some research challenges.
This work provided a framework for facial expression
recognition that can effectively maximize performance
22. REFERANCE
[1]Anjana R., Lavanya M. “Facial Emotions Recognition
System For Autism” International Journal of Advanced
Engineering Technology -June,2014 /40-43
[2] F. Bourel, C.C. Chibelushi, A.A. Low, "Robust Facial
Expression Recognition Using a State-Based Model of
Spatially-Localised Facial Dynamics", Proc. Fifth IEEE Int.
Conf. Automatic Face and Gesture Recognition, pp. 106-111,
2002
[3] F. Bourel, Models of Spatially-Localised Facial
Dynamics for Robust Expression Recognition, Ph.D.
Thesis, Staffordshire University, 2002
[4] V. Bruce, "What the Human Face Tells the Human
Mind: Some Challenges for the Robot-Human Interface",
Proc. IEEE Int. Workshop Robot and Human Communication,
pp. 44-51, 1992