Emotion Recognition

Project Title

Emotion Recognition

Project Area of Specialization Artificial IntelligenceProject Summary

Recent studies of emotion mindreading reveal that for three emotions, fear, disgust, and anger, deficits in face-based recognition are paired with deficits in the production of the same emotion.

This project aims to classify the emotion on a person's face into one of seven categories using deep convolutional neural networks. The model is trained on the dataset which was published on International Conference on Machine Learning (ICML). This dataset consists of 35887 grayscale, 48x48 sized face images with seven emotions: angry, disgusted, fearful, happy, neutral, sad and surprised.

Project Objectives

The objectives of the Project is to find the emotions of the employee in the office. We can monitor the activity of a children at school who is a fresh student. An interviewee can be given any scenario to judge his stress during interview for job. You can use this project anywhere you want to monitor the emotion of any person or group of person.

Project Implementation Method

A camera is needed that will record real time video of the place where the person is sitting. The video will be sent to the model and model will detect the emotions of the person. OR

Directly laptop can be used to record the video and process at the same time depending on the the circumstances.

Benefits of the Project

Every boss would like to know the mental condition of his employee whether he/she is capable of bearing the pressure of work or not. He can measure it before and after giving the job.

Similarly, In different schools teachers will be happy to know the emotions of a children during the school timings. Parents will be more satisfy.

Technical Details of Final Deliverable

• First, the haar cascade method is used to detect faces in each frame of the webcam feed.

• The region of image containing the face is resized to 48x48 and is passed as input to the CNN.

• The network outputs a list of softmax scores for the seven classes of emotions.

• The emotion with maximum score is displayed on the screen.

Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	72000
Blackmagic Pocket Cinema 4K	Equipment	1	38000	38000
MSI GTX 750Ti 2GB	Equipment	1	24000	24000
Maintinance	Miscellaneous	1	10000	10000