Human Emotion Recognition System

This work try to address the problem of emotion recognition from an image based and a deep neural network based approach. Emotion recognition is still a difficult and a complex problem in computer science. We chose facial expressions for the recognition of emotions in humans. Based on the feature po

2025-06-28 16:32:57 - Adil Khan

Project Title

Human Emotion Recognition System

Project Area of Specialization Computer ScienceProject Summary

This work try to address the problem of emotion recognition from an image based and a deep neural network based approach. Emotion recognition is still a difficult and a complex problem in computer science. We chose facial expressions for the recognition of emotions in humans. Based on the feature points within the face a deep neural network was trained to identify the emotions contained. In order to enhance accuracy, we are still testing it by using multiple different techniques. 

Project Objectives

The emotions are the easier way to detect person’s mood.

So by considering moods of the person we can easily communicate or handle any situation.

We want a system to be efficient in such a way that it helps users to detect the mood of a person through emotions.

This can enhance the comfort level during communication.

Trying to control the scenario in the real-time environment.

Project Implementation Method

Database creation was the major chellenge. We accepted it and created own datbase (videos) from different universities. 

We are working on % basic emotions: happy, sad, angry, shocked, normal.

For frames, we catagorize the emotions. Then we extracted the features.

Our data is trained for the dataset we made.

Our next step will be for real-time emotion detection.  

Benefits of the Project

On spot emotion recognition.

As social media chatting is common, due to emojis. So we want to enhance the comfort level in face to face communication. 

Emotion recognition in health care.

Saving costs and making life better for users

Technical Details of Final Deliverable

Final delivered system will firstly detect a face. 

It will recognize the face features, then on set parameters it will detect the type of emotion.

Finally the system will be able to detect the different emotions.

Final Deliverable of the Project HW/SW integrated systemCore Industry SecurityOther Industries Security Core Technology Artificial Intelligence(AI)Other Technologies Artificial Intelligence(AI)Sustainable Development Goals Industry, Innovation and InfrastructureRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 80000
NVIDIA GTX 1050 4GB Graphics Card Equipment14000040000
Usb Cameras Equipment31000030000
Conference publication fee Miscellaneous 11000010000

More Posts