Review of methods and techniques on Mind Reading Computer Machine
1. STUDENT DETAILS Guide Details
D.Madhavi Latha Mrs.M.Jyothi
Information Technology Dept of IT (GMRIT)
REVIEW OF METHODS AND TECHNIQUES ON
MIND READING COMPUTER MACHINE
Mind reading is a way to detect or infer other’s mental
states. The simplest way for mind reading can be done by
simply seeing and understanding the facial expression. For
example, a smile can give us an expression of happiness. But
now it may be possible that a computer might understand the
mental states of a person. The key to this scheme is the
electroencephalograph, a device used by medical
researchers to pick up electrical currents from various parts
of the brain. If we could learn to identify brain waves
generated by specific thoughts or commands, we might be
able to teach the same skill to a computer.
oPeople express their mental states, including emotions,
thoughts, and desires, all the time through facial
oOur mental states shape the decisions that we make, govern
how we communicate with others, and affect our
oTheory of mind or mind reading: The ability to attribute
mental states to others from their behavior and to use that
knowledge to guide our own actions and predict those of
oThe understanding of a human’s thoughts is one of the most
4. LITERATURE REVIEW
oFacial expression analysis includes both measurement of
facial motion and recognition of expression. The automatic
facial expression recognition problem is a very challenging
oThe proposed automatic facial expression recognition
system can automatically detect human faces, extract facial
features, and recognize facial expressions. Facial
expressions are the facial changes in response to a person’s
internal emotional states, intentions, or communications.(2)
oDuring tracking detailed parametric description of facial
features are extracted. The face can express emotion
sooner than people verbalize or even realize their
5. WHAT IS MIND READING?
oThe team member of University of Cambridge had been
working on a model of mind reading in a computer
laboratory and has developed mind reading machines that
implement a computational model of mind reading to infer
mental states of human being from their facial expressions
and head gestures.
oThe machine works by using digital video cameras which
analyzes a person’s facial expression in real time and infer
person’s underlying mental state such as thinking,
confused, interested, bored, agreeing, disagreeing, happy,
sad and angry.
6. WHYMIND READING?
oImagine a future, where we are surrounded with mobile
phones, cars and online services that can read our minds
and react to our moods.
oJust imagine how would that change our use of technology
and our lives?
oThe mind-reading computer system may also be used to
monitor and suggest improvements in human-human
oTo detect driver mental states such as drowsiness,
distraction and anger.
7. HOW DOES IT WORK?
oFuturistic Head Band:
Different sensors are fixed all around the futuristic head
band which measures the blood pressure ,impulses,
temperature of brain, volume and oxygen level of the blood
around the subjects of brain using technology called
Functional Near-Infrared Spectroscopy (FNIRS) and sends
this information to the computer which helps to find
whether the person is in happy mood or in aggressive
8. HOW DOES IT WORK? Continued…
It sends light in that spectrum into the tissues of the head,
where it is absorbed by active, blood-filled tissues.
The headband measures how much light was not absorbed,
letting the computer gauge the metabolic demands that the
brain is making.
For example, a combination of a head nod, with a smile
and eyebrows raised might mean interest.
oFacial Expressions analysis:
The face is one of the most powerful channel of non-verbal
9. HOW DOES IT WORK? Continued…
Facial expression provides clues about emotions, intention,
alertness, pain, regulates interpersonal behavior and
Facial expression analysis includes both measurement of
facial motion and recognition of expression.
Next step is to extract and represent the facial changes.
In facial feature extraction, there are two ways: geometric
feature based and appearance based methods.
The geometric feature presents the shape and location to
form a feature vector for facial components.
10. HOW DOES IT WORK? Continued…
In appearance- based method, image filters are applied
either to whole face or specific regions in a face image to
extract a feature vector.
Basic structure of facial expression analysis includes three
things. They are Face Acquisition, Facial Data Extraction
& Representation, Facial Expression Recognition.
11. HOW DOES IT WORK? Continued…
Facial expression recognition is based on technology of
Emotient. Emotient is an image recognition technology. It
allows faces, emotions, and other features to be recognized
and identified in photos and images.
After reading the image, the image must be analysed
So that correlation of the matrix will be find.
Since the correlation matrix for each image is square,
we can calculate Eigen vector and Eigen value for
These are very important so that it gives useful
information about the data.
13. TECHNIQUES continued…
Eigen Vectors and Eigen Value :
In Eigen vectors any vector change in magnitude but
not in direction.
In Eigen values, the magnitude that the vector is
changed is called an Eigen value
Where A is n x n matrix.
x is the length of n column vector.
λ is a scalar it’s an Eigen value and
X is the Eigen vector.
14. TECHNIQUES continued…
“The Eigen values for angry image 1:” 0.1369, 0.1371,
0.1372, 0.1373, 0.1371, 0.1368, 0.1366, 0.1375, 0.1382,
0.1285, 0.1394, 0.1402, 0.1406, 0.1408, 0.1412, 0.1417,
“The Eigen values for angry image2:” 0.1368, 0.1371,
0.1374, and 0.1372.
Figure 1. Angry expression for different situations
16. TECHNIQUES continued…
“The Eigen values for angry image3:” 0.1367, 0.1371,
0.1375 and 0.1371.
It is important to notice that these eigen vectors are both
unit eigen vectors that is their lengths are both 1.
After getting the Eigen values we calculate the mean
values for all the images, in order to get highest Eigen
The highest Eigen value must contain important feature
about the data.
So we select ten highest Eigen values from all the
17. RESULTS CAN BE EVALUATED IN THE
oThe results are often compared to a Magnetic Resonance
Imaging (MRI), but can be gathered with light weight, non
oWearing the FNIRS sensor, experimental subjects were
asked to count the number of squares on a rotating on
screen cube and to perform other tasks.
18. RESULTS CAN BE EVALUATED IN THE
FOLLOWING WAY continued…
o Measuring mental workload, frustration and distraction is
typically limited to qualitatively observing computer users.
oPreliminary results are shown using button sized sensors.
o"Biological signals arise when reading or speaking to
oneself with or without actual lip or facial movement”.
19. ADVANTAGES & USES
oCan read minds.
oHelp paralytic patients.
oHelp Handicapped people.
oHelp Comma patients.
oHelp people who can’t speak
oCan be used for mind gaming.
o Eliminate the capability to lie.
oTransmit visual images to the mind of a blind person,
allowing them to see.
oIt helps injured astronauts to control their machines or
aid disabled people.
21. It is little different from the Brain-Computer Typing
machine, this thing works by mapping brain waves when
you think about moving left, right, forward or back, and
then assigns that to a wheel chair.
This device allows people who can’t use other wheel chairs
to get around easier & will be able to move their
wheelchair with very less effort.
oBrain-Computer Typing machine
By thinking about left and right hand movement, user can
control the virtual keyboard.
Tufts University researchers have begun a three-year
research project which, if successful, will allow computers
to respond to the brain activity of the computer's user.
These computers can perform telepathy , by translating
brain activity into word.
The mental state is recognized by comparing the present
real time video with the preinstalled videos which contain
different expressions for different mental state.
It represents one of the most complicated and interesting
cognitive activities in which we routinely engage.
oCohn J. F., Tian, Kanade, T., (2001)”Recognizing action
units for facial expression analysis”, IEEE Transactions on
Pattern Analysis and Machine Intelligence, Vol. 23, No. 2.
oJ. Lien, A. Zlochower, J.Cohn and T. Kanade. Automated
facial expression recognition. In Proceedings of IEEE
International Conference on Automatic Face and Gesture
oY.-L. Tian, T. Kanade, and J.Cohn. Recognizing action
units for facial expression analysis. IEEE Transactions
on Pattern Analysis and Machine Intelligence,
23(2):97–115, February 2001.