Open raniasyed opened 3 months ago
Hello @raniasyed, Thank you for generating an issue to this project! Please wait while we get back to you.
Please assign this issue to me under WOC'24.
If the issue is currently open, please assign this task to me under GSSoC'24.
I am a contributor from GSOC'24 ,please assign this task to me
I am a contributor from GSOC'24 ,please assign this task to me
If the issue is currently open, please assign this task to me under GSSoC'24. I would get the work done. I have sufficient experience and knowledge in sentiment analysis.
If the issue is currently open, please assign this task to me under GSSoC'24. I would get the work done. I have sufficient experience and knowledge in computer vision.
I create a CNN model to to classify facial expressions into different emotion categories, including anger, disgust, fear, happiness, sadness, surprise, and neutrality in images as well as on a recorded videos and evaluate model on different performance metrics . I would like to assign this project to me as part of GSSoC'24 with the gssoc label and the appropriate level (1/2/3).
Hello, I'm Dheeraj currently working on machine learning models. I would like to solve this issue kindly allot it to me.
I agree to follow this project's Code of Conduct I'm a GSSOC'24 contributor I want to work on this issue
Hi @raniasyed ,
I have recognized the issue regarding facial sentiments based on features issue, e.g., "the misclassification of neutral expressions as negative sentiment". The solution involved libraries or modules languages describe the fix, e.g., "augmenting the dataset with more varied samples and fine-tuning the model". Please give me the chance and let me do the further adjustments that are needed.
Best, Darakhshan
I wanna fix this issue @akshitagupta15june
@akshitagupta15june could you please Assign me this issue??
@akshitagupta15june can u please assign me this issue ?
Facial expression analysis, a crucial aspect of sentiment analysis, involves interpreting emotional states based on facial features. In this project, we aim to develop a robust sentiment analysis system leveraging deep learning techniques to classify facial expressions into different emotion categories, including anger, disgust, fear, happiness, sadness, surprise, and neutrality. The proposed system will utilize a dataset of grayscale facial images, each labeled with the corresponding emotion category. By implementing state-of-the-art deep learning architectures, such as the ResNet model, we intend to train a model capable of accurately recognizing and classifying facial expressions in real-time. This project holds significant potential in various applications, including human-computer interaction, market research, customer feedback analysis, and mental health assessment.
To develop the Sentiment Analysis project based on Facial Features, the main steps required are:
1) Data Preprocessing 2) Model Selection and Architecture Design 3) Training and Validation 4) Evaluation 5) Deployment and Integration