SlideShare a Scribd company logo
Phase - 1
Seminar Presentation on
Emotion Detection of Babies’ Emotional Face using Deep Learning
Presented By-
Takrim Ul Islam Laskar
Roll No. 170302005
M.Tech 3rd Sem
Gauhati University Institute of Science And Technology
Dept. of Information Technology,Gauhati University
Under guidance of Dr. Parishmita Sarma
Assistant Professor, Dept. of IT,
Gauhati University.
Contents
• Introduction
• Computer Vision
• Face Detection
• Facial Landmark
• Machine Learning
• Artificial Neural Network
• Deep Learning
• Tools and Environment
• Proposed Methodology
• Result
• Conclusion and future work
Introduction.
• Emotion is a psychological and physiological state which is subject to
different conditions of mind. Broadly classifying happiness, sadness,
anger, disgust, surprise and fear are some of them.
• Human being is well capable of identifying emotions by observing the
actions of the subject. We are to build a system that makes a
computer capable to do the same.
• Pose, speech, facial expression, behaviour, etc convey emotions of
individuals but facial expression is the most precise to detect.
Computer Vision.
• Human beings are capable of seeing the world and objects with the
help of the eyes and act accordingly.
• The computers should be availed a system through which the
aforementioned task can be accomplished.
• Therefore, the system through which a computer undergoes a similar
task of seeing is referred to as computer vision.
Face Detection.
• To be able to identify the facial emotion, the fast and
foremost task is to locate the area in the image
where the face is available.
• There are many approaches to detect faces in a
digital image. Some of them are face detection with
controlled background, colour, motion, etc.[7]
Fig. Face Detection
Facial Landmark Detection
• Localization of Facial features like eyes, eyebrows, nose, mouth,
jawline can be achieved through Histogram of oriented gradients
(HOG), Haar wavelets, etc
• Applications of facial landmark detection[16]:
• Face recognition.
• Head pose estimation.
• Face morphing.
• Virtual makeup.
• Face replacement.
Machine Learning
• ML algorithms build a mathematical model of sample data known as
training data with the help of which it makes predictions and
decisions without explicitly running certain commands.
• More the size of samples, better is the performance and more is the
accuracy.
• Machine Learning uses two types of techniques: Supervised Learning
and Unsupervised Learning.
Supervised Learning[12] [17].
• Supervised Learning trains a model on known input and output data so that it
can predict future outputs.
• Supervised learning uses classication and regression techniques:
• Classification techniques predict discrete responses. Classification models
classify input data into categories. Typical applications include medical imaging,
speech recognition, etc.
• Regression techniques predict continuous responses like changes in
temperature or fluctuations in power demand. Typical applications include
electricity load forecasting and algorithmic trading.
Fig. Types of Machine Learning
Unsupervised Learning.
• Unsupervised Learning finds hidden patterns or intrinsic structures in data. It
is used to draw inferences from datasets consisting of input data without
labeled responses.
• Clustering is the most common unsupervised learning technique. It is used for
exploratory data analysis to find hidden patterns or groupings in data.
Applications for cluster analysis include gene sequence analysis, market
research, and object recognition
Fig. Clustering of patterns
Artificial Neural Network[14] [18]
• Artificial Neural Networks are computer systems designed based on
biological neural networks which constitute the animal brain.
• Biological Neurons
• A nerve cell (neuron) is a special biological cell that processes information.
• According to an estimation, there are huge number of neurons, approximately
1011
with numerous interconnections, approximately 1015
.
Working of Biological Neural network
• Dendrites- They are tree-like branches, responsible for receiving the
information from other neurons it is connected to.
• Soma- It is the cell body of the neuron and is responsible for processing of
information, they have received from dendrites.
• Axon- It is just like a cable through which neurons send the information.
• Synapses- It is the connection between the axon and other neuron
dendrites.
Fig. Biological Neural Network
Analogy of ANN and BNN
Biological Neural Network
(BNN)
Articial Neural Network
(ANN)
Dendrites Input
Soma Node
Axon Output
Synapse Weights or Interconnections
Fig. Analogy of ANN and BNN.
Model of Artificial Neural network
• The following diagram represents the general model of ANN followed by its
processing.
For the above general model of articial neural network, the net input can be calculated as follows-
Net Input, 𝑦𝑖𝑛 = 𝑥1. 𝑤1 + 𝑥2. 𝑤2 + 𝑥3. 𝑤3…… 𝑥 𝑚. 𝑤 𝑚
i.e., 𝑦𝑖𝑛 = 𝑖
𝑚
𝑥𝑖 𝑤𝑖
The output can be calculated by applying the activation function over the net input.
Y = F( 𝑦𝑖𝑛)
Deep Learning.[13]
• Deep Learning is a class of machine learning algorithms that use a cascade
of multiple layers of parallel processing units.
• Each successive layer uses the output from the previous layer as input.
• It learns in supervised or/and unsupervised manner.
Fig. Multiple layer NN in Deep Learning
Tools and Environment.
• Tools
• Python
• openCV
• Dlib
• Camera
• Dependencies
• Shape_predictor_68_face_landmarks.dat
• Imutils
• Environment
• Operating System- Ubuntu 16.04 (Linux based plateform)
• RAM- 4GB
• Processor- Intel core i5 7th Gen.
Proposed Methodology
• The proposed system enable a computer to detect the seven
universal emotions of human baby through detection of facial
expressions.
• The system may be useful in health care centres for automated
surveillance of psychological and physiological state of babies through
detection of facial expressions in real-time.
Proposed Methodology(cont.)
• Image Acquisition - The frame from the real-
time video would be the image.
• Face Detection - Dlib's frontal face detector
is used for detection of face in the image.
• Landmark Detection - Facial feature or
landmark is then extracted. These features
include ears, eyebrows, nose, mouth,
jawline.
• Neural Network - The data from the feature
points is then fed to the NN for classication
of emotions.
• After classication, the result of the
expression is then reflected to the image
using image tagging.
Fig. Block Diagram proposed methodology
Flow of the project
Fig. Flowchart of the project
Image Acquisition
The images have to be loaded first from the storage for training and testing the
Neural Network Classifiers.
To do so, openCV function cv2.imread() is used.
• Colour- cv2.imread(`image',1)
• Grayscale- cv2.imread(`image',0)
• Unchanged- cv2.imread(`image',-1)
To read image as CLI argument, function cv2.imread(args["image"]) is used.
To read image from directory:
directry=os.path.join(os.getcwd(), `dir')
cv2.imread(directory+'/'+image)
Fig. Image Acquisition.
Preprocessing.
After loading the image, pre-processing is done by resizing the image to 500
pixels and converting the resized image to grayscale.
• Resizing
• Scaling down the images allow faster processing.
• Moreover the images have to be of the same size to train a neural
network.
• To resize the images imutils function imutils.resize(image, width=500) is
used.
• Grayscale Conversion
• The openCV supports BGR colour model and dlib supports RGB colour
model. And grayscale color model is supported in both.
• Grayscale colour model is used for 2D image processing.
• Edges are better depicted in grayscale images.
• To convert the image to grayscale openCV function cv2.cvtColor(image,
cv2.COLOR _BGR2GRAY) is used.
Fig. Image Resizing.
Fig. Grayscale Conversion
Face Detection
• We used frontal_face_detector which comes with dlib
library.
• It is based on Histogram of Oriented Gradiants(HOG)
features and Support Vector Machine(SVM).
• The model is built out of 5 HOG filters which are front
looking, left looking, right looking, front looking but
rotated left and front looking but rotated right.
• The dataset used for training consisted of 2825
images, obtained from LFW dataset and manually
annotated by Davis King, the author of dlib.
Fig. Face detection.
Facial landmark extraction
• We have used the dlib's shape predictor and analysed
the dataset images with a pretrained file,
‘shape_predictor_68_face_landmarks.dat’ to get the
facial landmarks detected.
• An ensemble of regression trees is used to train the
file for estimation the facial landmark positions
through pixel intensities themselves.
• The facial landmark detector is used to estimate the
location of 68 (x , y)-coordinates that map to facial
structure on the face.
• The facial landmarks are thereby detected and are
ready to be fed to the the Convolutional Neural
Network.
Fig. Detection of Facial
Landmark.
Annotations based on 68 point iBUG 300-W
dataset.
Facial Landmark Points
Jaw 1-17
Right Eyebrow 18-22
Left Eyebrow 23-27
Nose 28-36
Right Eye 37-42
Left Eye 43-48
Mouth 49-68
Fig. Annotations based on 68 point iBUG 300-W dataset.
Training Neural network Classifier
• In the phase-2 of the project, a good amount of images of babies with
different emotions will be collected. These datasets would be used to
train Convolutional Neural Network(CNN) Classifiers.
• This would be done by feeding the coordinates of the landmarks
extracted from the images.
• Each emotion would generate particular mathematical instances after
training. These instances would be used to detect the emotions of
facial expression.
• 90% of the images would be used as training dataset.
Testing Neural network Classifier
• The trained Classifiers are then tested with a dataset of images which
were not used for training the classifiers.
• 10% of the images would be used as a testing dataset. The true
positive and false positive of the classification is then used to
calculate the accuracy of the System.
Result
• In the system, face detection and facial landmark detection have been
done successfully.
Fig. Face and landmark Detection on Image with Multiple Faces.
Conclusion and future work
• In this paper we have developed a system for facial landmark detection to detect
seven human emotions through detection of facial expressions.
• For that, we first detected the faces in the image using dlib's face detector. Then,
we extracted the 68 facial landmarks like eyes, eyebrow, nose, mouth, jawline
using dilb's shape predictor with the help of
shape_predictor_68_face_landmarks.dat file.
• In the next phase of the project the objective is to use a Convolutional Neural
Network to train classifiers to detect the emotions.
• The classifier is a statistical model which is created by the neural network based
on the image data used to train the NN classifier. The NN classifier would be then
tested with test dataset to calculate the accuracy of detection.
• The final output would be a system capable of detecting the emotions based on
facial expressions of babies.
References.
[1] D. R. Frischholz. (2018) Face detection algorithms techniques. [Online]. Available:
https://facedetection.com/algorithms/
[2] V. Gupta. (2018) Face detection { opencv, dlib and deep learning ( c++ / python ). [Online].
Available: https://www.learnopencv.com/face-detection-opencv-dlib-and-deep-learning-c-python/
[3] G. Hemalatha and C. Sumathi, A study of techniques for facial detection and expression classication,"
International Journal of Computer Science and Engineering Survey, vol. 5, no. 2, p. 27, 2014.
[4] D. E. King. (2018) Dlib c++ library. [Online]. Available: http://dlib.net/
[5] S. Mallick. (2015) Facial landmark detection. [Online]. Available: https://www.learnopencv.com/facial-
landmark-detection/
[6] openCV team. (2018) Opencv documentation. [Online]. Available: https://opencv.org/
[7] . M. Pantic, Facial expression recognition," Imperial College London, London, UK; University of
Twente, AE Enschede, The Netherlands, 2008.
[8] M. Pantic, L. Rothkrantz, and H. Koppelaar, Automation of non-verbal communication of facial
expressions," in Proc. Conf. Euromedia, 1998, pp. 86{93.
References.
[9] A. Pascu, B. A. Intelligence, and R. King, Facial expression recognition system," University of Manchester,
2015.
[10] T. V. Pham, M. Worring et al., Face detection methods, a critical evaluation," 2000.
[11] T. V. Pham, M. Worring, and A. W. Smeulders, Face detection by aggregated bayesian network classiers,"
Pattern Recognition Letters, vol. 23, no. 4, pp. 451{461, 2002.
[12] A. Savoiu and J. Wong, Recognizing facial expressions using deep learning."
[13] M. team. (2016) Machine learning. [Online]. Available: https://in.mathworks.com/discovery/machine-
learning.html
[14] T. team. (2015) Articial neural network - basic concepts. [Online]. Available:
https://www.tutorialspoint.com/articial neural network/articial neural network basic concepts.htm
[15] W. N. Widanagamaachchi, Facial emotion recognition with a neural network approach,“ University of
Colombo, 2009.
[16] Wikipedia. (2016) Articial neural network. [Online]. Available: https://en.wikipedia.org/wiki/Articial neural
network
[17] Wikipedia. (2016) Machine learning. [Online]. Available: https://en.wikipedia.org/wiki/Machine learning
[18] Wikipedia.. (2017) Deep learning. [Online]. Available: https://en.wikipedia.org/wiki/Deep learning
Thank You.

More Related Content

What's hot

Emotion recognition using image processing in deep learning
Emotion recognition using image     processing in deep learningEmotion recognition using image     processing in deep learning
Emotion recognition using image processing in deep learning
vishnuv43
 
Facial expression recognition
Facial expression recognitionFacial expression recognition
Facial expression recognition
ElyesMiri
 
4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognitionNgaire Taylor
 
Facial Emotion Recognition: A Deep Learning approach
Facial Emotion Recognition: A Deep Learning approachFacial Emotion Recognition: A Deep Learning approach
Facial Emotion Recognition: A Deep Learning approach
AshwinRachha
 
EMOTION DETECTION USING AI
EMOTION DETECTION USING AIEMOTION DETECTION USING AI
EMOTION DETECTION USING AI
Aantariksh Developers
 
Facial Expression Recognition (FER) using Deep Learning
Facial Expression Recognition (FER) using Deep LearningFacial Expression Recognition (FER) using Deep Learning
Facial Expression Recognition (FER) using Deep Learning
Emmeline Tsen
 
Facial Emoji Recognition
Facial Emoji RecognitionFacial Emoji Recognition
Facial Emoji Recognition
ijtsrd
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection System
Abhiroop Ghatak
 
Introduction to emotion detection
Introduction to emotion detectionIntroduction to emotion detection
Introduction to emotion detection
Tyler Schnoebelen
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGY
JASHU JASWANTH
 
Face detection ppt
Face detection pptFace detection ppt
Face detection ppt
Pooja R
 
Facial recognition technology by vaibhav
Facial recognition technology by vaibhavFacial recognition technology by vaibhav
Facial recognition technology by vaibhavVaibhav P
 
Facial expression recognition system : survey
Facial expression recognition system : surveyFacial expression recognition system : survey
Facial expression recognition system : survey
Mohamed Alhmdany
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection Abu Saleh Musa
 
Facial Expression Recognition via Python
Facial Expression Recognition via PythonFacial Expression Recognition via Python
Facial Expression Recognition via Python
Saurav Gupta
 
Facial emotion recognition
Facial emotion recognitionFacial emotion recognition
Facial emotion recognitionAnukriti Dureha
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural networkSmriti Tikoo
 
Face recognization
Face recognizationFace recognization
Face recognization
leenak770
 
FACIAL EXPRESSION RECOGNITION 1 2.pptx
FACIAL EXPRESSION RECOGNITION 1 2.pptxFACIAL EXPRESSION RECOGNITION 1 2.pptx
FACIAL EXPRESSION RECOGNITION 1 2.pptx
Yash670955
 
Face Detection
Face DetectionFace Detection
Face Detection
Reber Novanta
 

What's hot (20)

Emotion recognition using image processing in deep learning
Emotion recognition using image     processing in deep learningEmotion recognition using image     processing in deep learning
Emotion recognition using image processing in deep learning
 
Facial expression recognition
Facial expression recognitionFacial expression recognition
Facial expression recognition
 
4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition4837410 automatic-facial-emotion-recognition
4837410 automatic-facial-emotion-recognition
 
Facial Emotion Recognition: A Deep Learning approach
Facial Emotion Recognition: A Deep Learning approachFacial Emotion Recognition: A Deep Learning approach
Facial Emotion Recognition: A Deep Learning approach
 
EMOTION DETECTION USING AI
EMOTION DETECTION USING AIEMOTION DETECTION USING AI
EMOTION DETECTION USING AI
 
Facial Expression Recognition (FER) using Deep Learning
Facial Expression Recognition (FER) using Deep LearningFacial Expression Recognition (FER) using Deep Learning
Facial Expression Recognition (FER) using Deep Learning
 
Facial Emoji Recognition
Facial Emoji RecognitionFacial Emoji Recognition
Facial Emoji Recognition
 
Automated Face Detection System
Automated Face Detection SystemAutomated Face Detection System
Automated Face Detection System
 
Introduction to emotion detection
Introduction to emotion detectionIntroduction to emotion detection
Introduction to emotion detection
 
FACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGYFACE RECOGNITION TECHNOLOGY
FACE RECOGNITION TECHNOLOGY
 
Face detection ppt
Face detection pptFace detection ppt
Face detection ppt
 
Facial recognition technology by vaibhav
Facial recognition technology by vaibhavFacial recognition technology by vaibhav
Facial recognition technology by vaibhav
 
Facial expression recognition system : survey
Facial expression recognition system : surveyFacial expression recognition system : survey
Facial expression recognition system : survey
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection
 
Facial Expression Recognition via Python
Facial Expression Recognition via PythonFacial Expression Recognition via Python
Facial Expression Recognition via Python
 
Facial emotion recognition
Facial emotion recognitionFacial emotion recognition
Facial emotion recognition
 
Detection and recognition of face using neural network
Detection and recognition of face using neural networkDetection and recognition of face using neural network
Detection and recognition of face using neural network
 
Face recognization
Face recognizationFace recognization
Face recognization
 
FACIAL EXPRESSION RECOGNITION 1 2.pptx
FACIAL EXPRESSION RECOGNITION 1 2.pptxFACIAL EXPRESSION RECOGNITION 1 2.pptx
FACIAL EXPRESSION RECOGNITION 1 2.pptx
 
Face Detection
Face DetectionFace Detection
Face Detection
 

Similar to Facial emotion detection on babies' emotional face using Deep Learning.

Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep Learning
Aashish Chaubey
 
Elderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detectionElderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detection
Tanvi Mittal
 
ppt.pdf
ppt.pdfppt.pdf
Thesis presentation
Thesis presentationThesis presentation
Thesis presentation
Aras Masood
 
Project report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptxProject report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptx
taxihig737
 
Final year ppt
Final year pptFinal year ppt
Final year ppt
Shruti Chandra
 
Face recognition using artificial neural network
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural networkSumeet Kakani
 
Image recognition
Image recognitionImage recognition
Image recognition
Aseed Usmani
 
FACE RECOGNITION USING ELM-LRF
FACE RECOGNITION USING ELM-LRFFACE RECOGNITION USING ELM-LRF
FACE RECOGNITION USING ELM-LRF
Aras Masood
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
Takrim Ul Islam Laskar
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Ali Alkan
 
Image recognition
Image recognitionImage recognition
Image recognition
Nikhil Singh
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
SurajKumar579888
 
IRJET- Emotion Classification of Human Face Expressions using Transfer Le...
IRJET-  	  Emotion Classification of Human Face Expressions using Transfer Le...IRJET-  	  Emotion Classification of Human Face Expressions using Transfer Le...
IRJET- Emotion Classification of Human Face Expressions using Transfer Le...
IRJET Journal
 
Paper of Final Year Project.pdf
Paper of Final Year Project.pdfPaper of Final Year Project.pdf
Paper of Final Year Project.pdf
MuhammadAsfandyarJan1
 
Face Detection and Recognition using Back Propagation Neural Network (BPNN)
Face Detection and Recognition using Back Propagation Neural Network (BPNN)Face Detection and Recognition using Back Propagation Neural Network (BPNN)
Face Detection and Recognition using Back Propagation Neural Network (BPNN)
IRJET Journal
 
Deep learning.pptx
Deep learning.pptxDeep learning.pptx
Deep learning.pptx
MdMahfoozAlam5
 
Emotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.pptEmotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.ppt
Gopi Naidu
 
Week1- Introduction.pptx
Week1- Introduction.pptxWeek1- Introduction.pptx
Week1- Introduction.pptx
fahmi324663
 
introdaction.pptx
introdaction.pptxintrodaction.pptx
introdaction.pptx
Dekebatufa
 

Similar to Facial emotion detection on babies' emotional face using Deep Learning. (20)

Face Recognition - Deep Learning
Face Recognition - Deep LearningFace Recognition - Deep Learning
Face Recognition - Deep Learning
 
Elderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detectionElderly Assistance- Deep Learning Theme detection
Elderly Assistance- Deep Learning Theme detection
 
ppt.pdf
ppt.pdfppt.pdf
ppt.pdf
 
Thesis presentation
Thesis presentationThesis presentation
Thesis presentation
 
Project report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptxProject report of thr facial expressionppt.pptx
Project report of thr facial expressionppt.pptx
 
Final year ppt
Final year pptFinal year ppt
Final year ppt
 
Face recognition using artificial neural network
Face recognition using artificial neural networkFace recognition using artificial neural network
Face recognition using artificial neural network
 
Image recognition
Image recognitionImage recognition
Image recognition
 
FACE RECOGNITION USING ELM-LRF
FACE RECOGNITION USING ELM-LRFFACE RECOGNITION USING ELM-LRF
FACE RECOGNITION USING ELM-LRF
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine LearningMakine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
Makine Öğrenmesi ile Görüntü Tanıma | Image Recognition using Machine Learning
 
Image recognition
Image recognitionImage recognition
Image recognition
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
 
IRJET- Emotion Classification of Human Face Expressions using Transfer Le...
IRJET-  	  Emotion Classification of Human Face Expressions using Transfer Le...IRJET-  	  Emotion Classification of Human Face Expressions using Transfer Le...
IRJET- Emotion Classification of Human Face Expressions using Transfer Le...
 
Paper of Final Year Project.pdf
Paper of Final Year Project.pdfPaper of Final Year Project.pdf
Paper of Final Year Project.pdf
 
Face Detection and Recognition using Back Propagation Neural Network (BPNN)
Face Detection and Recognition using Back Propagation Neural Network (BPNN)Face Detection and Recognition using Back Propagation Neural Network (BPNN)
Face Detection and Recognition using Back Propagation Neural Network (BPNN)
 
Deep learning.pptx
Deep learning.pptxDeep learning.pptx
Deep learning.pptx
 
Emotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.pptEmotion recognition and drowsiness detection using python.ppt
Emotion recognition and drowsiness detection using python.ppt
 
Week1- Introduction.pptx
Week1- Introduction.pptxWeek1- Introduction.pptx
Week1- Introduction.pptx
 
introdaction.pptx
introdaction.pptxintrodaction.pptx
introdaction.pptx
 

Recently uploaded

Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
Aditya Rajan Patra
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
Kamal Acharya
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
JoytuBarua2
 
Online aptitude test management system project report.pdf
Online aptitude test management system project report.pdfOnline aptitude test management system project report.pdf
Online aptitude test management system project report.pdf
Kamal Acharya
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
Victor Morales
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Soumen Santra
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
bakpo1
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
Kamal Acharya
 
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABSDESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
itech2017
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
Kamal Acharya
 
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
Amil Baba Dawood bangali
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
gestioneergodomus
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
zwunae
 
Fundamentals of Induction Motor Drives.pptx
Fundamentals of Induction Motor Drives.pptxFundamentals of Induction Motor Drives.pptx
Fundamentals of Induction Motor Drives.pptx
manasideore6
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
Intella Parts
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
Osamah Alsalih
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
SamSarthak3
 
Swimming pool mechanical components design.pptx
Swimming pool  mechanical components design.pptxSwimming pool  mechanical components design.pptx
Swimming pool mechanical components design.pptx
yokeleetan1
 
Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024
Massimo Talia
 
digital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdfdigital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdf
drwaing
 

Recently uploaded (20)

Recycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part IIIRecycled Concrete Aggregate in Construction Part III
Recycled Concrete Aggregate in Construction Part III
 
Student information management system project report ii.pdf
Student information management system project report ii.pdfStudent information management system project report ii.pdf
Student information management system project report ii.pdf
 
Planning Of Procurement o different goods and services
Planning Of Procurement o different goods and servicesPlanning Of Procurement o different goods and services
Planning Of Procurement o different goods and services
 
Online aptitude test management system project report.pdf
Online aptitude test management system project report.pdfOnline aptitude test management system project report.pdf
Online aptitude test management system project report.pdf
 
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsKuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressions
 
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTSHeap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
Heap Sort (SS).ppt FOR ENGINEERING GRADUATES, BCA, MCA, MTECH, BSC STUDENTS
 
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
一比一原版(SFU毕业证)西蒙菲莎大学毕业证成绩单如何办理
 
Water billing management system project report.pdf
Water billing management system project report.pdfWater billing management system project report.pdf
Water billing management system project report.pdf
 
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABSDESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
DESIGN AND ANALYSIS OF A CAR SHOWROOM USING E TABS
 
Cosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdfCosmetic shop management system project report.pdf
Cosmetic shop management system project report.pdf
 
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单专业办理
 
Fundamentals of Induction Motor Drives.pptx
Fundamentals of Induction Motor Drives.pptxFundamentals of Induction Motor Drives.pptx
Fundamentals of Induction Motor Drives.pptx
 
Forklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella PartsForklift Classes Overview by Intella Parts
Forklift Classes Overview by Intella Parts
 
MCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdfMCQ Soil mechanics questions (Soil shear strength).pdf
MCQ Soil mechanics questions (Soil shear strength).pdf
 
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdfAKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
 
Swimming pool mechanical components design.pptx
Swimming pool  mechanical components design.pptxSwimming pool  mechanical components design.pptx
Swimming pool mechanical components design.pptx
 
Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024Nuclear Power Economics and Structuring 2024
Nuclear Power Economics and Structuring 2024
 
digital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdfdigital fundamental by Thomas L.floydl.pdf
digital fundamental by Thomas L.floydl.pdf
 

Facial emotion detection on babies' emotional face using Deep Learning.

  • 1. Phase - 1 Seminar Presentation on Emotion Detection of Babies’ Emotional Face using Deep Learning Presented By- Takrim Ul Islam Laskar Roll No. 170302005 M.Tech 3rd Sem Gauhati University Institute of Science And Technology Dept. of Information Technology,Gauhati University Under guidance of Dr. Parishmita Sarma Assistant Professor, Dept. of IT, Gauhati University.
  • 2. Contents • Introduction • Computer Vision • Face Detection • Facial Landmark • Machine Learning • Artificial Neural Network • Deep Learning • Tools and Environment • Proposed Methodology • Result • Conclusion and future work
  • 3. Introduction. • Emotion is a psychological and physiological state which is subject to different conditions of mind. Broadly classifying happiness, sadness, anger, disgust, surprise and fear are some of them. • Human being is well capable of identifying emotions by observing the actions of the subject. We are to build a system that makes a computer capable to do the same. • Pose, speech, facial expression, behaviour, etc convey emotions of individuals but facial expression is the most precise to detect.
  • 4. Computer Vision. • Human beings are capable of seeing the world and objects with the help of the eyes and act accordingly. • The computers should be availed a system through which the aforementioned task can be accomplished. • Therefore, the system through which a computer undergoes a similar task of seeing is referred to as computer vision.
  • 5. Face Detection. • To be able to identify the facial emotion, the fast and foremost task is to locate the area in the image where the face is available. • There are many approaches to detect faces in a digital image. Some of them are face detection with controlled background, colour, motion, etc.[7] Fig. Face Detection
  • 6. Facial Landmark Detection • Localization of Facial features like eyes, eyebrows, nose, mouth, jawline can be achieved through Histogram of oriented gradients (HOG), Haar wavelets, etc • Applications of facial landmark detection[16]: • Face recognition. • Head pose estimation. • Face morphing. • Virtual makeup. • Face replacement.
  • 7. Machine Learning • ML algorithms build a mathematical model of sample data known as training data with the help of which it makes predictions and decisions without explicitly running certain commands. • More the size of samples, better is the performance and more is the accuracy. • Machine Learning uses two types of techniques: Supervised Learning and Unsupervised Learning.
  • 8. Supervised Learning[12] [17]. • Supervised Learning trains a model on known input and output data so that it can predict future outputs. • Supervised learning uses classication and regression techniques: • Classification techniques predict discrete responses. Classification models classify input data into categories. Typical applications include medical imaging, speech recognition, etc. • Regression techniques predict continuous responses like changes in temperature or fluctuations in power demand. Typical applications include electricity load forecasting and algorithmic trading. Fig. Types of Machine Learning
  • 9. Unsupervised Learning. • Unsupervised Learning finds hidden patterns or intrinsic structures in data. It is used to draw inferences from datasets consisting of input data without labeled responses. • Clustering is the most common unsupervised learning technique. It is used for exploratory data analysis to find hidden patterns or groupings in data. Applications for cluster analysis include gene sequence analysis, market research, and object recognition Fig. Clustering of patterns
  • 10. Artificial Neural Network[14] [18] • Artificial Neural Networks are computer systems designed based on biological neural networks which constitute the animal brain. • Biological Neurons • A nerve cell (neuron) is a special biological cell that processes information. • According to an estimation, there are huge number of neurons, approximately 1011 with numerous interconnections, approximately 1015 .
  • 11. Working of Biological Neural network • Dendrites- They are tree-like branches, responsible for receiving the information from other neurons it is connected to. • Soma- It is the cell body of the neuron and is responsible for processing of information, they have received from dendrites. • Axon- It is just like a cable through which neurons send the information. • Synapses- It is the connection between the axon and other neuron dendrites. Fig. Biological Neural Network
  • 12. Analogy of ANN and BNN Biological Neural Network (BNN) Articial Neural Network (ANN) Dendrites Input Soma Node Axon Output Synapse Weights or Interconnections Fig. Analogy of ANN and BNN.
  • 13. Model of Artificial Neural network • The following diagram represents the general model of ANN followed by its processing. For the above general model of articial neural network, the net input can be calculated as follows- Net Input, 𝑦𝑖𝑛 = 𝑥1. 𝑤1 + 𝑥2. 𝑤2 + 𝑥3. 𝑤3…… 𝑥 𝑚. 𝑤 𝑚 i.e., 𝑦𝑖𝑛 = 𝑖 𝑚 𝑥𝑖 𝑤𝑖 The output can be calculated by applying the activation function over the net input. Y = F( 𝑦𝑖𝑛)
  • 14. Deep Learning.[13] • Deep Learning is a class of machine learning algorithms that use a cascade of multiple layers of parallel processing units. • Each successive layer uses the output from the previous layer as input. • It learns in supervised or/and unsupervised manner. Fig. Multiple layer NN in Deep Learning
  • 15. Tools and Environment. • Tools • Python • openCV • Dlib • Camera • Dependencies • Shape_predictor_68_face_landmarks.dat • Imutils • Environment • Operating System- Ubuntu 16.04 (Linux based plateform) • RAM- 4GB • Processor- Intel core i5 7th Gen.
  • 16. Proposed Methodology • The proposed system enable a computer to detect the seven universal emotions of human baby through detection of facial expressions. • The system may be useful in health care centres for automated surveillance of psychological and physiological state of babies through detection of facial expressions in real-time.
  • 17. Proposed Methodology(cont.) • Image Acquisition - The frame from the real- time video would be the image. • Face Detection - Dlib's frontal face detector is used for detection of face in the image. • Landmark Detection - Facial feature or landmark is then extracted. These features include ears, eyebrows, nose, mouth, jawline. • Neural Network - The data from the feature points is then fed to the NN for classication of emotions. • After classication, the result of the expression is then reflected to the image using image tagging. Fig. Block Diagram proposed methodology
  • 18. Flow of the project Fig. Flowchart of the project
  • 19. Image Acquisition The images have to be loaded first from the storage for training and testing the Neural Network Classifiers. To do so, openCV function cv2.imread() is used. • Colour- cv2.imread(`image',1) • Grayscale- cv2.imread(`image',0) • Unchanged- cv2.imread(`image',-1) To read image as CLI argument, function cv2.imread(args["image"]) is used. To read image from directory: directry=os.path.join(os.getcwd(), `dir') cv2.imread(directory+'/'+image) Fig. Image Acquisition.
  • 20. Preprocessing. After loading the image, pre-processing is done by resizing the image to 500 pixels and converting the resized image to grayscale. • Resizing • Scaling down the images allow faster processing. • Moreover the images have to be of the same size to train a neural network. • To resize the images imutils function imutils.resize(image, width=500) is used. • Grayscale Conversion • The openCV supports BGR colour model and dlib supports RGB colour model. And grayscale color model is supported in both. • Grayscale colour model is used for 2D image processing. • Edges are better depicted in grayscale images. • To convert the image to grayscale openCV function cv2.cvtColor(image, cv2.COLOR _BGR2GRAY) is used. Fig. Image Resizing. Fig. Grayscale Conversion
  • 21. Face Detection • We used frontal_face_detector which comes with dlib library. • It is based on Histogram of Oriented Gradiants(HOG) features and Support Vector Machine(SVM). • The model is built out of 5 HOG filters which are front looking, left looking, right looking, front looking but rotated left and front looking but rotated right. • The dataset used for training consisted of 2825 images, obtained from LFW dataset and manually annotated by Davis King, the author of dlib. Fig. Face detection.
  • 22. Facial landmark extraction • We have used the dlib's shape predictor and analysed the dataset images with a pretrained file, ‘shape_predictor_68_face_landmarks.dat’ to get the facial landmarks detected. • An ensemble of regression trees is used to train the file for estimation the facial landmark positions through pixel intensities themselves. • The facial landmark detector is used to estimate the location of 68 (x , y)-coordinates that map to facial structure on the face. • The facial landmarks are thereby detected and are ready to be fed to the the Convolutional Neural Network. Fig. Detection of Facial Landmark.
  • 23. Annotations based on 68 point iBUG 300-W dataset. Facial Landmark Points Jaw 1-17 Right Eyebrow 18-22 Left Eyebrow 23-27 Nose 28-36 Right Eye 37-42 Left Eye 43-48 Mouth 49-68 Fig. Annotations based on 68 point iBUG 300-W dataset.
  • 24. Training Neural network Classifier • In the phase-2 of the project, a good amount of images of babies with different emotions will be collected. These datasets would be used to train Convolutional Neural Network(CNN) Classifiers. • This would be done by feeding the coordinates of the landmarks extracted from the images. • Each emotion would generate particular mathematical instances after training. These instances would be used to detect the emotions of facial expression. • 90% of the images would be used as training dataset.
  • 25. Testing Neural network Classifier • The trained Classifiers are then tested with a dataset of images which were not used for training the classifiers. • 10% of the images would be used as a testing dataset. The true positive and false positive of the classification is then used to calculate the accuracy of the System.
  • 26. Result • In the system, face detection and facial landmark detection have been done successfully. Fig. Face and landmark Detection on Image with Multiple Faces.
  • 27. Conclusion and future work • In this paper we have developed a system for facial landmark detection to detect seven human emotions through detection of facial expressions. • For that, we first detected the faces in the image using dlib's face detector. Then, we extracted the 68 facial landmarks like eyes, eyebrow, nose, mouth, jawline using dilb's shape predictor with the help of shape_predictor_68_face_landmarks.dat file. • In the next phase of the project the objective is to use a Convolutional Neural Network to train classifiers to detect the emotions. • The classifier is a statistical model which is created by the neural network based on the image data used to train the NN classifier. The NN classifier would be then tested with test dataset to calculate the accuracy of detection. • The final output would be a system capable of detecting the emotions based on facial expressions of babies.
  • 28. References. [1] D. R. Frischholz. (2018) Face detection algorithms techniques. [Online]. Available: https://facedetection.com/algorithms/ [2] V. Gupta. (2018) Face detection { opencv, dlib and deep learning ( c++ / python ). [Online]. Available: https://www.learnopencv.com/face-detection-opencv-dlib-and-deep-learning-c-python/ [3] G. Hemalatha and C. Sumathi, A study of techniques for facial detection and expression classication," International Journal of Computer Science and Engineering Survey, vol. 5, no. 2, p. 27, 2014. [4] D. E. King. (2018) Dlib c++ library. [Online]. Available: http://dlib.net/ [5] S. Mallick. (2015) Facial landmark detection. [Online]. Available: https://www.learnopencv.com/facial- landmark-detection/ [6] openCV team. (2018) Opencv documentation. [Online]. Available: https://opencv.org/ [7] . M. Pantic, Facial expression recognition," Imperial College London, London, UK; University of Twente, AE Enschede, The Netherlands, 2008. [8] M. Pantic, L. Rothkrantz, and H. Koppelaar, Automation of non-verbal communication of facial expressions," in Proc. Conf. Euromedia, 1998, pp. 86{93.
  • 29. References. [9] A. Pascu, B. A. Intelligence, and R. King, Facial expression recognition system," University of Manchester, 2015. [10] T. V. Pham, M. Worring et al., Face detection methods, a critical evaluation," 2000. [11] T. V. Pham, M. Worring, and A. W. Smeulders, Face detection by aggregated bayesian network classiers," Pattern Recognition Letters, vol. 23, no. 4, pp. 451{461, 2002. [12] A. Savoiu and J. Wong, Recognizing facial expressions using deep learning." [13] M. team. (2016) Machine learning. [Online]. Available: https://in.mathworks.com/discovery/machine- learning.html [14] T. team. (2015) Articial neural network - basic concepts. [Online]. Available: https://www.tutorialspoint.com/articial neural network/articial neural network basic concepts.htm [15] W. N. Widanagamaachchi, Facial emotion recognition with a neural network approach,“ University of Colombo, 2009. [16] Wikipedia. (2016) Articial neural network. [Online]. Available: https://en.wikipedia.org/wiki/Articial neural network [17] Wikipedia. (2016) Machine learning. [Online]. Available: https://en.wikipedia.org/wiki/Machine learning [18] Wikipedia.. (2017) Deep learning. [Online]. Available: https://en.wikipedia.org/wiki/Deep learning