Scribd Logo
Upload

Welcome to Scribd!

  • Seminar

    Uploaded by

    Shivam Prajapati
    11 views10 pages
    The document describes a project to develop a facial emotion detection system using a convolutional neural network (CNN) model. The CNN model is trained on a large dataset of faces labeled with seven basic emotions. It then aims to classify new input images of faces into one of the seven emotion categories. The methodology uses data preprocessing, image augmentation, CNN feature extraction and training to develop the model for classification. The accuracy of the trained model is then evaluated on a test dataset.

    Original Description:

    Original Title

    Seminar Ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    The document describes a project to develop a facial emotion detection system using a convolutional neural network (CNN) model. The CNN model is trained on a large dataset of faces labeled with seven basic emotions. It then aims to classify new input images of faces into one of the seven emotion categories. The methodology uses data preprocessing, image augmentation, CNN feature extraction and training to develop the model for classification. The accuracy of the trained model is then evaluated on a test dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    11 views10 pages

    Seminar

    Uploaded by

    Shivam Prajapati
    The document describes a project to develop a facial emotion detection system using a convolutional neural network (CNN) model. The CNN model is trained on a large dataset of faces labeled with seven basic emotions. It then aims to classify new input images of faces into one of the seven emotion categories. The methodology uses data preprocessing, image augmentation, CNN feature extraction and training to develop the model for classification. The accuracy of the trained model is then evaluated on a test dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 10

    Facial Emotion Detection using CNN

    Shivam Kumar Prajapati (191EC246)


    EC390 Seminar

    National Institute of Technology, Karnataka Surathkal

    12 Nov 2021

    SHIVAM PRAJAPATI Facial Emotions


    Introduction

    1 The facial expression of human emotion is one of the major


    topics in facial recognition, and it can generate both technical
    and everyday application beyond laboratory experiment .

    2 Emotion detection can give people more affinities and help to


    provide personalized service to people depending on their
    moods.

    3 This project constructs a system of deep learning model to


    classify a given image of human facial emotion into one of the
    seven basic human emotions .

    4 and the testing result will be evaluated based on accuracy of


    the model.

    SHIVAM PRAJAPATI Facial Emotions


    Objective

    1 There are several areas where the emotion recognition


    technique are used ,like in digital Cameras to automatically
    take pictures when the user smiles.

    2 However, the most promising applications involve the


    humanization of artificial intelligent systems.

    3 If computers are able to keep track of the mental status of the


    user, robots can react upon this and behave appropiately.

    4 Emotion recognition therefore plays a key-role in improving


    human machine interaction.

    SHIVAM PRAJAPATI Facial Emotions


    Methodology

    1 In this project, a deep learning technique called Convolutional


    Neural Networks(CNNs) to establish a classification model
    that combines feature extraction with classification.

    2 CNN model is built using keras library, optimiser used is adam


    and loss function used is categorical.

    SHIVAM PRAJAPATI Facial Emotions


    Steps :

    Data Preprocessing

    Image augmentation

    Feature Extraction

    Training

    Validation

    SHIVAM PRAJAPATI Facial Emotions


    Procedure

    1 Developing a CNN model.


    2 Training and testing on very large dataset (FER-2013 used for
    this project)
    3 Taking image of any dimension from user.

    4 Predicting emotion of input image.


    5 GPU enabled training is used for model (since it has 35000 +
    images.
    6 for creating model python libraries tensorflow, keras are used.
    7 other python libraries used are numpy, scipy, pandas etc.

    SHIVAM PRAJAPATI Facial Emotions


    Result :

    Input Image
    Result

    SHIVAM PRAJAPATI Facial Emotions


    Conclusion

    1 This project aims at detection of facial emotions.its programs


    classifies image given as input to one of the seven
    classes/emotions.(0=Angry, 1=Disgust, 2=Fear, 3=Happy,
    4=Sad, 5=Surprise, 6=Neutral)

    2 Keras library of python is used for building the model and the
    dataset used is FER2013.Images are downgraded to 48 x 48
    since the images present in the dataset were of this
    dimensions.

    SHIVAM PRAJAPATI Facial Emotions


    Advantages

    Better security. Face detection augments surveillance tactics


    and forms the basis of the identification process of terrorists
    and criminals.

    Easy to integrate. Most face detection solutions are


    compatible with security software.

    Automated identification. Face detection lets facial


    identification be automated, thus increasing efficiency
    alongside a heightened rate of accuracy.

    SHIVAM PRAJAPATI Facial Emotions


    References

    https://docs.opencv.org/master/da/df6/tutorial py table of
    contents setup.html

    Dennis Hamester et al., “Face Expression Recognition with a


    2-Channel Convolutional Neural Network”, International Joint
    Conference on Neural Networks (IJCNN), 2015.

    SHIVAM PRAJAPATI Facial Emotions

    You might also like