Professional Documents
Culture Documents
Facial expressions are among the most common ways that individuals
communicate.
expressions, but it is far more difficult for a computer system to do the same. It is
now possible to identify emotions from photographs thanks to recent
developments in computer vision and machine learning.
2
Objective
❀The idea is to replicate the human thought process based on training data
(in the form of images and videos of humans).
❀Computer systems today can work with digital images and videos to
understand and emotionally identify the characteristics of contents.
❀If computers able to keep track of the mental state of the user, robots can
react upon this and behave appropriately.
4
*Proposed system
The proposed system is capable of performing automatic facial
expressions of 5 basic emotions.
5
* Convolutional Neural Network
Deep Learning has established itself as a very potent tool over the last few
decades due to its capacity for handling massive amounts of data.
6
Basic Expressions
Python 3
above
Windows 10 and above
Hardware Requirements :
System with Intel Pentium Core i3 and above
8
*Technology used
Convolutional Neural Networks (CNN)
TensorFlow library
Keras library
Open CV library
Matplotlib library
Matplotlib.pyplot library
Numpy library 9
*Feasibility study
*Technical feasibility
This study is carried out to check the technical feasibility, that is, the
technical requirements of the system.
Any system developed must not have a high demand on the available
technical resources. This will lead to high demands being placed on the
client.
11
*Economical feasibility
Thus, the developed system as well within the budget and this
12
*Operational feasibility
This includes the process of training the user to use the system
efficiently.
13
Workflow
14
E-R
Diagram
15
Sequence
Diagram
16
*I/O screens
Emotion: Happy
18
Emotion: Neutral
19
Emotion: Sad
20
Emotion: Angry
21
Emotion: Surprise
22
*Applications
It can be used in healthcare to detect depression.
23
*Future scope
We will work to add other complex emotions such as fear, empathy,
Some bug fixes for any issues which may occur while implementing.
24
*Conclusion
We used the power of Artificial Intelligence to work on Cognitive Science and
dealt with human faces, this term is generally referred to as Computer
Vision. We were able to extract emotions out of photos and videos of human
faces.
This was our project about “Human Emotion Detection” developed based on
Python programming language.
We assume this system gave numerous delight to everyone. although every
task is never said to be ideal in this development field even more
improvement can be viable in this application.
We discovered so many things and received plenty of information about
development field. we are hoping this could prove fruitful to us.
25
*Acknowledgement
We would like to thank our teacher Miss. Latika Chame who continuously
lot.
26
*Reference
https://machinelearningmastery.com/how-to-use-transfer-learning-when-developing-
convolutional-neural-network-models/
https://towardsdatascience.com/transfer-learning-using-mobilenet-and-keras-
c75daf7ff299
http://ieeexplore.ieee.org/document/7013165/
https://www.analyticsvidhya.com/blog/2018/08/a-simple-introductionto-facial-
recognition-with-python-codes
https://realpython.com/face-recognition-with-python/
http://web.stanford.edu/class/ee368/Project_Autumn_1617/Reports/
report_pao.pdf
https://sci-hub.se/10.1109/INCET49848.2020.9154121
https://link.springer.com/article/10.1007/s42452-020-2234-1
27
Thank You.
28