Sentitect Emotion Classifier

An emotion Detection System is a modern approach towards the solution of human-computer interaction or robot-human interaction. While communicating, emotions are the first thing that is analyzed by a person or machines, and in order to recognize those expressions or emotions by machines, we would ha

Project Title

Sentitect Emotion Classifier

Project Area of Specialization

Artificial Intelligence

Project Summary

An emotion Detection System is a modern approach towards the solution of human-computer interaction or robot-human interaction. While communicating, emotions are the first thing that is analyzed by a person or machines, and in order to recognize those expressions or emotions by machines, we would have to design a system in such a way that machines can detect human emotions. The final deliverable will be in the form of web-based software in which the screen will be depicting the user's face, and a label will be highlighting their expressions.

Project Objectives

Our project objective is to design an emotion detection system from which machines can easily interpret human emotions. To feed human emotions, we have to train machines according to our needs, and for that, we would be using deep learning to teach the machines about human emotions.

Project Implementation Method

To cater to the emotion detection problem among machines, we would be building an emotion detection system that we will build on the framework of deep learning. We will train the machine with existent datasets of human emotions and will then compare it with real-time face detection. For this, we would be using Python as our basic language along with the CNN algorithm. The purpose of using CNN is its higher accuracy. The multi-layer algorithm refines the raw data to its meaningful form. CNN would be applied to real-time data that we would be collecting with the help of High Definition WebCam so that a clear picture can be captured. We would be using OpenCV software to map the face of real-time computer vision. The real-time data would then be compared with the pre-stored data set of human emotions. We would be taking 7 universally recognized human expressions i.e. happy, sad, angry, neutral, disgust, fear, and surprise. We would be then training the machine with Keras, in python for the CNN algorithm and would be exporting NumPy and panda for array classification. Conclusively after training the machines with human expressions, we would be successfully categorizing human emotions. Our project adjective is to design an emotion detection system from which machines can easily interpret human emotions. To feed human emotions, we have to train machines according to our needs, and for that, we would be using deep learning to teach the machines about human emotions. To cater to the emotion detection problem among machines, we would be building an emotion detection system that we will build on the framework of deep learning. We will train the machine with existent datasets of human emotions and will then compare it with real-time face detection. For this, we would be using Python as our basic language along with the CNN algorithm. The purpose of using CNN is its higher accuracy. The multi-layer algorithm refines the raw data to its meaningful form. CNN would be applied to real-time data that we would be collecting with the help of High Definition WebCam so that a clear picture can be captured. We would be using OpenCV software to map the face of real-time computer vision. The real-time data would then be compared with the pre-stored data set of human emotions. We would be taking 7 universally recognized human expressions i.e. happy, sad, angry, neutral, disgust, fear, and surprise. We would be then training the machine with Keras, in python for the CNN algorithm and would be exporting NumPy and panda for array classification. Conclusively after training the machines with human expressions, we would be successfully categorizing human emotions. Our project adjective is to design an emotion detection system from which machines can easily interpret human emotions. To feed human emotions, we have to train machines according to our needs, and for that, we would be using deep learning to teach the machines about human emotions.

Benefits of the Project

• Machines can better understand human expressions and emotions while communicating, especially virtual AI chatbots, IoT devices and etc.
• It will help teachers in jotting live feedbacks of particular sessions from students in online learning sessions
• It will help doctors in monitoring patients expression during various mental therapies i.e. in EEG
• Can lower crimes by detecting their expressions and activity from CCTV cameras

Technical Details of Final Deliverable

The final deliverable will be in the form of web-based software in which the screen will be depicting the user's face, and a label will be highlighting their expressions.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

IT

Other Industries

Education , Medical , Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Internet of Things (IoT), Augmented & Virtual Reality, Robotics

Sustainable Development Goals

Good Health and Well-Being for People, Quality Education, Sustainable Cities and Communities

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com