Scribd
Upload
14 views3 pages

Weekly Report 9

Uploaded by

mathandass5555
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
14 views3 pages

Weekly Report 9

Uploaded by

mathandass5555
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

19CS71C- Research Paper and Patent Review

Weekly Report - 9

Title: Emotion Detection Using Deep Learning


Reg No: 2112033
Name: G. Abishek
Domain: Deep Learning

Problem Statement:
The challenge of accurately recognizing and interpreting human facial emotions from
various angles and perspectives poses significant difficulties in the fields of medical research
and computer science. Traditional methods in facial emotion recognition (FER) rely on
feature extraction and feature selection using Convolutional Neural Networks (CNNs).
However, these methods often struggle with images that are not captured from a frontal view,
limiting their effectiveness in real-world applications. This limitation is particularly critical
for enhancing patient care and supporting children with speech impairments, where accurate
emotion detection can provide essential psychological insights.The proposed research aims to
develop an advanced facial emotion recognition model utilizing a Bi-Directional Long Short-
Term Memory (Bi-LSTM) network. This model seeks to overcome the limitations of
conventional CNN-based approaches by accurately recognizing facial emotions from images
captured at various angles. The primary objective is to create a robust system that can identify
and interpret a wide range of emotional states, enhancing its application in medical and social
contexts.

No. of Papers Reviewed: 2

Paper 1:
Title: Facial Emotion Detection Using Haar Cascade and CNN Algorithm
Authors: Nongmeikapam Thoiba Singh, Ritu, Samridh Rana, Sonal Kumari
Publisher: IEEE
Date of Publication: August 2023
Proposed Work: The paper presents a method combining the Haar Cascade and CNN for
facial emotion detection. The Haar Cascade is employed for facial feature detection (eyes,
nose, mouth), while the CNN classifies the features into one of seven emotions. The method
is tested on the CK+ dataset, achieving a high accuracy of 98.42%.
Paper 2:

Title: Facial Image PreProcessing and Emotion Classification: A Deep Learning Approach
Authors: Alramzana Nujum Navaz, Serhani Mohamed Adel, Sujith Samuel Mathew
Publisher: IEEE
Date of Publication: 2019

Proposed Work: This paper introduces a solution for improving emotion detection accuracy
by applying preprocessing techniques combined with deep learning models. Preprocessing
includes image quality enhancement and noise reduction, followed by emotion classification
using AlexNet and GoogLeNet models. The study achieves a significant accuracy
improvement with enhanced images.

Comparative Analysis:

Content Paper 1 Paper 2


Objective Develop a facial emotion Enhance emotion detection
detection system using Haar accuracy by applying image
Cascade for feature pre-processing techniques
detection and CNN for and deep learning models.
classification of emotions.
Dataset Used CK+ dataset with seven Indian Movie Face Database
basic emotions (anger, (IMFDB) consisting of
happiness, sadness, etc.). images of Indian actors with
various emotions.
Technique Used Combination of Haar
Pre-processing techniques
Cascade for facial feature
for image quality
detection and CNN for
improvement, followed by
emotion classification.
classification using
AlexNet and GoogLeNet.
Modules Description 1. Feature Detection using 1. Image Pre-processing for
Haar Cascade 2. Emotion quality enhancement 2.
Classification using CNN 3. Deep Learning-based
Model Testing and emotion classification using
Validation on CK+ dataset AlexNet and GoogLeNet 3.
Evaluation of models with
and without image
enhancement
Performance Measure Achieved 98.42% accuracy Significant accuracy
on CK+ dataset using the improvements through pre-
Haar Cascade and CNN processing and deep
approach. learning, with over 93%
accuracy using enhanced
images.
Future Work 1. Explore additional deep 1. Extend the study to cover
learning models like real-time videos 2. Combine
attention processes and emotion detection with EEG
transfer learning 2. Apply signals for medical
the approach in augmented applications.
reality, psychology, and
human-computer interaction.

Conclusion:
Both papers emphasize improvements in facial emotion detection using deep learning
techniques, but they focus on different aspects. Paper 1 highlights the combination of Haar
Cascade and CNN to detect facial features and classify emotions with a high level of
accuracy. Paper 2, on the other hand, focuses on enhancing the quality of input images before
classification, significantly improving accuracy with preprocessing techniques. The proposed
BiLSTM model in the current research seeks to further enhance these approaches by
improving emotion recognition from various angles and perspectives, offering potential
applications in medical research and human interaction systems.

Project Guide Course Instructor

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy