“Human Face

Detection and
Emotion
Recognition
Using OpenCV
through AI ”
 Introduction
• In the world of computer vision, choosing
OpenCV for human face detection and
emotion recognition is a wise and exciting
venture.
• OpenCV, a powerful open-source library,
employs sophisticated algorithms to identify
faces in images or video streams.
• It not only spots faces but also delves into
the realm of emotions, decoding smiles,
frowns, and expressions with remarkable
accuracy.
• This dynamic duo of face detection and
emotion recognition opens doors to diverse
applications, from security systems to
interactive user experiences.
• With OpenCV's user-friendly interface and
robust capabilities, exploring the nuances of
human expression becomes an accessible
and thrilling journey.
 Literature Survey
1.Author’s used Eigen Face, Fisher Face, and LBPH (Local Binary Patterns Histogram) algorithm
in [1]. The study focused on automatic face recognition and detection using and the camera.
OpenCV, specifically utilizing the Haar Cascade classifier and recognizer for frontal faces. It
reported 100% accuracy in three different algorithms (Eigen Face, Fisher Face, and LBPH) up to a
distance of 70 cm between the person and the camera.
2.Authors used Haar Cascade classifier, LBPH recognizer in [8]. This study implemented face
detection and recognition using OpenCV focusing on the Haar Cascade classifier and LBPH
recognizer algorithms.
3. Authors used Haar Cascade classifier, LBPH recognizer in [5]. This study implemented Human
Face Recognition Applying Haar Cascade Classifier. .
Additionally, advancements in real-time face detection and recognition using OpenCV and Python
have been documented. For example:
4. Authors used Haar Cascade, Eigen Face, LBP (Local Binary Pattern), Fisher Faces, LBPH (Local
Binary Pattern Histogram), Yolo, Faster R-CNN, Single-shot Detectors (SSD) in [6]. The study
implemented Real-Time face detection and face recognition using OpenCV and python and
compared various algorithms for real-time face detection and recognition, including Haar Cascade,
Eigen Face, LBP, Fisher Faces, Yolo, Faster R-CNN, and SSDs.
These studies collectively highlight the diverse range of algorithms and methodologies employed
in human face detection and recognition, showcasing advancements in accuracy, real-time
performance, and algorithmic comparisons.
 Motivation
Choosing human face detection and emotion recognition
using OpenCV can be motivated by several factors, as Here
are some motivations for pursuing this area:
1.Ubiquity of Faces:
Faces are ubiquitous in daily life, making face detection a
fundamental step in many computer vision applications.
2.Security and Surveillance:
Face detection is crucial in security and surveillance
systems.
3.Human-Computer Interaction (HCI):
Emotion recognition adds a layer of complexity to human-
computer interaction. 4.Healthcare Applications:
Emotion recognition can be applied in healthcare settings,
helping to monitor patients' emotional states and well-
being.
5.Education and Research:
Face detection and emotion recognition can be used in
educational settings for assessing student engagement and
understanding
 Literature Survey
Research Paper Published Conclusion

Automatic face recognition 16 June 2020 Algorithm Used:

and detection using Eigen Face ,Fisher Face and LBPH Algorithm
OpenCV, Haar cascade and
recognizer for frontal face. Distance B/w Person and Camera: up to 70 cm
Z Arya, V Tiwari - Int. J. Eng.
Res. Appl. www. ijera. com, Accuracy: 100 % Accurate in three different algorithms up to 70 cm
2020

Face Detection and 24 October2021 Algorithms used:

Recognition Using OpenCV. Haar Cascade, Eigen Face ,LBP(Local Binary Pattern),Fisher Faces,
TH. Hasan, R., & Bibo Sallow, LBPH(Local Binary Pattern Histogram),Yolo, Faster R-CNN,Single
A. . (2021). shot Detectors(SSD).
->In this they made a Comparision between the algorithms.

Facial Emotion Detection 23 May 2021 Algorithm Used:

Using Deep Learning and Haar cascade face Identification Algorithm
Haar Cascade Face
Identification Algorithm. Accuracy:The accuracy of the given technique is trailed on popular
B Alankar, MS Ammar, H FER2013 facial expression dataset, and it achieves 91.85% accuracy
Kaur - Advances in of the given dataset.
Intelligent Computing and
Face Recognition 8 May 2021 Algorithm Used:
using Open CVPranav Verma, Haar cascade Classifier, LBPH recognizer
P. Renukadevi, HiraSohail
Accuaracy : 90 -95%

Human Face Recognition Applying Haar 1 January 2022 Algorithm Used:

Cascade ClassifierF. M. Javed Mehedi Haar cascade classifier , LBPH recognizer
Shamrat, Anup Majumder, Probal Roy
Antu, Saykot Kumar Barmon, Itisha
Nowrin & Rumesh Ranjan

Real Time Face Detection and Face June 2022 Algorithm Used:
Recognition using OpenCV and Python. Haar Cascade, Eigen Face ,LBP(Local
P Chandrakala, B Srinivas, MA Kumar Binary Pattern),Fisher Faces,
LBPH(Local Binary Pattern
Histogram),Yolo, Faster R-CNN,Single shot
Detectors(SSD).
->In this they made a Comparision
between the algorithms.
Block Diagram - Workflow of Emotion Recognition

PIP Install facial- Configuring Torch for

Install Pytorch libraries
emotion-recognition CPU

Obtaining face emotions

Display The Output Frame
by passing libraries.
Libraries Used :-
1. Scikit-image It includes algorithms for segmentation, geometric transformations, color
space manipulation ,analysis,
filtering ,morphology, features detection and more.
2.PIL It adds support for opening ,manipulating and saving many different
image file formats.
3.Open CV Open CV is a library of programming functions mainly aimed at real-time
computer vision.

4.Mahotas Mahotas is a includes many algorithms implemented in C++ for speed

while operating in numpy arrays and with a very clean python interface.

5.Scientific Python Scipy contains modules for optimization , Linear algebra , integration,
interpolation, special functions , FFT, signal and image processing.

6.Numerical Python Numpy is a library for the python programming language ,adding support
for large , multi-dimensional arrays and matrices, along with a large
collection of high-level mathematical functions to operate on these arrays.
• Installing Libraries
Facial Emotion recognition: pip install facial-
emotion-recognition

• Configuring Torch for CPU :-

./site-package/torch/serialization.py

• Change:
def load(f, map_location=None,
pickle_module=pickle, **pickle_load_args):
to
def load(f, map_location='cpu',
pickle_module=pickle, **pickle_load_args):
 Conclusion
• In conclusion, delving into Human Face Recognition
and Emotion Detection using OpenCV reveals a
fascinating world where technology interprets our
expressions.
• OpenCV, with its smart algorithms, not only spots
faces but also deciphers emotions like smiles and
frowns.
• It's like giving computers the ability to understand
how we feel! The technology is handy for various
cool things, from security systems to making
interactive gadgets.
• It's impressive how OpenCV turns pixels into
emotions, making human-computer interaction a lot
more engaging and fun. So, in a nutshell, OpenCV is
like a digital emotion detective, making technology
more human-friendly and exciting !
References
[1] F. Javed Mehedi Shamrat, A. Majumder, P. Antu, S.
Barmon and I. Nowrin, Human Fcae Recognition Applying
Haar Cascade Classifier, Harvard: Springer Singapore., 2022.

[2] P. Chandrakala, B. Srinivas and M. Anil Kumar, Real Time

Face Detection and Face Recognition using OpenCV and
Python, Harvard: JesPublication, 2022.

[3] Z. Arya and V. Tiwari, Automatic face recognition and

detection using OpenCV, haar cascade and recognizer for
frontal face, harvard: www.ijera.com, 2020.

[4]R. Hasan and A. Sallow, Face Detection and Recognition

Using OpenCV, Harvard: Journal of Soft Computing and Data
Mining,, 2021.

[5] B. Alankar , M. Ammar and H. Kaur , Facial Emotion

Detection Using Deep Learning and Haar Cascade Face
Identification Algorithm., Harvard: springer Singapore,
2021.
6] P. Verma, P. Renukadevi and H. Sohail, Face recognition using openCV., Harvard:
Annals of the Romanian Society for Cell Biology,, 2021.

[7] J. Hicks, Emotion Detection Using OpenCV for Automatic Facial, Harvard:
earlham.edu, 2019.

[8] P. Saini, . B. Nagpal, S. Kaushik and P. Gupta, Face Recognition in Real Time Video
using HaarCascade Classifier, Harvard: INDIACom, 2019.

[9] A. Kumar, S. Chaudhary, S. Sangal and R. Dhama, Face Detection and Recognition
using OpenCV, Harvard: International Journal of Computer Applications, 2022.

[10] A. Ahmad, S. Saon, C. Abd Kadir Mahamad, S. Wiwoho, S. Mudjanarko and M.

Hariadi, Real time face recognition of video surveillance system using haar cascade
classifier., Harvard: Indonesian Journal of Electrical Engineering and Computer
Science, 2021.
THANK YOU