Behavoral facial recognition coding system

Project Title

Behavoral facial recognition coding system

Project Area of Specialization Artificial IntelligenceProject Summary

Emotions are complex processes involving multiple response channels, including physiological systems, facial expression and voices. Bio-signals reflect sequences of neural activity, which result in changes in autonomic and neuroendocrine systems induced by emotional events. Therefore in human computer interaction researches on of the most current interesting topics in emotion recognition is to recognize human’s feelings using bio signals. The aim of this study is to classify emotions (joy, sadness, anger, fear, surprise, disgust and neutral) that human have often experienced in real life from multi-channel bio-signals using machine learning algorithms.

Project Objectives

The others done this project in a simple way like emotions are detected simply by face. In market there are different types of solutions available like voice detection, iris detection, hand writing detection, gesture detection. But all these features are implemented separately. We will combine all these techniques in one tool.

Project Implementation Method

Doctor’s D Methodology

The above giving proposed method is how it is going to apply this on this thesis.

From the above given method, it shall only be working on the domain which is in the red box, why, because for the thesis requirement. Besides the red box, the text and EEG is also a complete domain of analysis, in autism.

1. Pre-processing

In the phase of pre-processing, the dataset of 3 autistic and 3 normal person has been train on our method, which a sure that our method/methodology is better than others used in the past. In our pre-processing methodology the patient is tend to play a game, the age in this thesis targeting is 17-21 years old. During the play few pictures had been captured by the HD cam, which help our recognizer to make a result. The result has been calculated using D’s method which include FAC, for emotional recognition. This is very first time FACS shall be used for Autistic patients.

While living in Pakistan this is one of its very own research on autism, using any computer aided technique.

1. Facial Action Coding System

The Facial Action Coding System (FACS) refers to a set of facial muscle movements that correspond to a displayed emotion. Originally created by Carl-Herman Hjortsjö with 23 facial motion units in 1970, it was subsequently developed further by Paul Ekman, and Wallace Friesen. The FACS as we know it today was first published in 1978, but was substantially updated in 2002. Further researchers worked on it and they had found that there are 64 facial motion units. But in this research we are going to implement just 24 of them, because autistic child don’t have the same facial expression as we normal people have, so in this case we just implement only 24 facial units.

For the pupil size detection we using Circular ring ray Algorithm, which works on the bases of iris points in an eye. The use of this algorithm, because of the autism. As we know the DSM-V Method, in which it was mentioned that autism is the psychological development disorder, and ASD is on that autism which are not able to detect easily.

Benefits of the Project

. In market there are different types of solutions available like voice detection, iris detection, hand writing detection, gesture detection. But all these features are implemented separately. We will combine all these techniques in one tool and recgnize 5 types of emotions.

Technical Details of Final Deliverable

Emotion recognition is the way to get the idea about human expression against human and other living beings. Autism is Humans have six basic emotions – happiness, surprise, sadness, anger, fear and disgust. We also experience more complex feelings like embarrassment, shame, pride, guilt, envy, joy, trust, interest, contempt and anticipation. The ability to understand and express these emotions starts developing from birth. From around two months, most babies will laugh and show signs of fear. Autism is one of major development disorder found in the children By 12 months, a typically developing baby can read your face to get an understanding of what you’re feeling. Most toddlers and young children start to use words to express feelings although you might see a tantrum or two when their feelings get too big for their words! Throughout childhood and adolescence, most children continue building empathy, self-regulation and skills in recognizing and responding to other people’s feelings. By adulthood, people are usually able to quickly recognize subtle emotional expressions. Most of the people and parents consider that their child is in some kind of trouble, but in-fact it is not a trouble, ASD can be cure if it diagnoses on the early stage. By using Machine Learning Techniques, we are able to diagnose the ASD and also the emotional state of a person.

Expression are the language of a person towards the next, while people who are victimize by ASD, their emotional expression are not that easy to be detected. By using our system, we are not just detecting or diagnose the emotions but also we are able to find the type of ASD, and according to that type we are able to get their emotion expression.

Final Deliverable of the Project Software SystemCore Industry ITOther Industries Education , Medical , Agriculture , Media , Security Core Technology Artificial Intelligence(AI)Other Technologies RoboticsSustainable 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)	10000
2	Miscellaneous	5	2000	10000