BSCS FINAL PROJECT PROPOSAL

Emotion Recognition by Facial Expressions

Term: Spring 2013

Presented by: Registration No: Name: L1F09BSCS2090 HASSAN SHABBIR L1F09BSCS2019 WALEED KHALID

Faculty of Information Technology

University of Central Punjab

ER System

Project Title Emotion Recognition by Facial Expressions

Project Advisor Prof. Yasir Danial Khan Particulars of the students:

S.No 1 2 Registration#
eg.L1F00MSCS0101

Name in Full
Use Block Letters

CGPA 2.49 2.23

Signatures

L1F09BSCS2090 L1F09BSCS2019

HASSAN SHABBIR
WALEED KHALID

Advisors Consent
I Prof./Dr./Mr./Ms. ________________________________________________ am willing to guide these students in all phases of above-mentioned project / thesis as advisor. I have carefully seen the Title and description of the project / thesis and believe that it is of an appropriate difficulty level for the number of students named above.

Note:
Advisor cant be changed without priorpermission of the Manager Projects and the duration for completion of Research Project / Thesis is 1 Year (approx.) from the date of Registration of Research Project/Thesis. Signatures and Date

Advisor

REFERENCE 1
I have carefully read the project proposal and feel that the proposed project is a useful one and of a sufficient difficulty level to justify a one year work load of above mentioned students. Recommended Yes No Signatures and Date

REFERENCE 2
I have carefully read the project proposal and feel that the proposed project is a useful one and of a sufficient difficulty level to justify a one year work load of above mentioned students. Recommended Yes No Signatures and Date

Page1

ER System

Abstract Emotions play a vital role in peoples everyday life. It is a mental state that does not arise through free will and is often accompanied by physiological changes. Therefore monitoring these changes is important as they are perceptions of emotional changes and can help in identifying matters of concern at an early stage before they become serious. Emotion recognition has become an important subject when it comes to human-machine interaction. Various methods have been used in past to detect and evaluate human emotions. The most commonly used techniques include the use of textual information, speech, body gestures and physiological signals. In this project we will develop an emotion recognition system based on information provided by the facial expressions. The four basic emotions observed in this project are happy (excited), sad, angry and neutral (relaxed). The data has been collected from healthy individuals, including both male and female. [1][2] Clear Statement of the Problem It is proposed to design a real time monitoring systems, capable of evaluating four basic emotions i.e. happy, sad, angry and neutral. In order to introduce affect recognition and its possible applications to the information security community. The implementation of these systems will represent the realization of an important goal for the security industry, the automation of real-time prediction of human behavior and intention. [2] If any company makes a funny/sad advertisement and they are not sure their advertisement is up to the mark. The implementation of these systems will help them to find out their advertisement is ready or not for market arranging test run by showing their advertisement to different sets of people. Objectives As we know, computers and robots are being used widely for betterment of our daily life therefore it is important for computers and robots to have an artificial mind that would enable them to communicate with human beings using both logical and emotional information and our main objective of this project is to design a real time monitoring systems, capable of evaluating four basic emotions i.e. happy, sad, angry and neutral.[2] The basic idea of emotion recognition using facial expression is to segment facial images into various regions of interest. The common regions taken into account include movements of cheeks, chin, eyes, eyebrows, and mouth. Different Classification techniques are then applied to differentiate between types of emotions. Motivation Over the past decades, human-computer interaction with computer vision has been an important field in computer study. It is concerned with the relationship of direct communication between the computer and human beings. Much research has been conducted on improving and developing the interaction between humans and the computer. Interested researchers worked on this area for different reasons. One of the significant factors that contributed to increasing and developing the interaction between the computer and humans is studying the computer's ability to distinguish emotions for
Signature Reference 1 Signature Reference 2

Page2

ER System

humans and the motivation for this project has stemmed from numerous sources. Firstly the desire is to work and create content with Image Processing and secondly I always have been keen to do things that are new, and push technology to set new foundations. I want to bring IP social interactions together to create a much more appealing and interactive social medium. Sometimes we are unable to find out the proper mood of the person during simple chat where cam is not available this thing will help to find out the mood by changing the background or sending the emotions automatically. (If angry backgrounds will be red). This software will help others software as well.

Introduction and Background Facial emotion recognition plays a vital role when it comes to developing multicultural visual communication systems for emotion translation between cultures. As we know computers and robots are being used widely for betterment of our daily life therefore it is important for computers and robots to have an artificial mind that would enable them to communicate with human beings using both logical and emotional information The basic idea of emotion recognition using facial expression is to segment facial images into various regions of interest. The common regions taken into account include movements of cheek, chin, wrinkles, eyes, eyebrows, and mouth. Different classification techniques are then applied to differentiate between different types of emotions. The analysis and evaluation of facial expressions. The proposed scheme used external stimulus to excite specific emotions in human subjects whose facial expressions were analyzed by segmenting and localizing the individual frames into regions of interest. Selected facial features such as eye opening, mouth opening. The system is developed to analyze the test data based on the provided training data to recognize the emotional states. Our System should recognize seven emotions anger, contempt, disgust, fear, joy, sadness, and surprise and also be able to detect emotions from video, image or real time facial expression. When we smile, frown or grimace, thousands of tiny facial muscles are at work. Emotion-recognition software, or ERS, creates a 3-D face map, pinpointing trigger areas like eye and mouth corners. Then a face-tracking algorithm matches the movements to basic expression patterns, corresponding to anger, sadness, fear, surprise, disgust and happiness, or a mixture of them. [3]

Signature Reference 1

Signature Reference 2

Page3

ER System

Related Work There is a vast body of literature on emotion. Emotion recognition has been investigated with the Speech and body gesture but the results are generally obtained with acted emotion database because they contain strong emotional expressions. Recent discoveries suggests that emotions are intricately linked to other functions Such as attention, perception, memory, decision making, and learning. In this, we concentrate on the expressive nature of emotion, especially those expressed on the face.

Project Plan / Schedule

Signature Reference 1

Signature Reference 2

Page4

ER System

Resources Required 1) Internet Connectivity 2) Pc 3) Web cam

References [1] M.Tauseef Quazi, Emotion recognition by using smart sensor ACM Digital Library, School of engineering and technology, Massey University, New Zealand, pp. 5-10, Feb 2012

[2]: ACM Joseph Burlington, Proceedings of the 2nd annual conference on Information security curriculum development, Georgia Southern University, Statesboro, GA, New York, USA, Pages 95-99, 2005 [3]: Nicole Martinelli, Emotion-Recognition Knows What Makes You Smile, University, Statesboro, GA, New York, USA, Pages 40-41-, 2007

[4] M. T. Quazi, Human Emotion Recognition Using Smart Sensors, Electronics, Information and Communication System (EICS) Seminar, 21st March 2011. Massey University, Palmerston North, New Zealand

Signature Reference 1

Signature Reference 2

Page5