Instant Download

Download your project material immediately after online payment.

Project File Details


3,000.00

100% Money Back Guarantee

File Type: MS Word (DOC) & PDF

File Size:  1,323KB

Number of Pages:42

 

ABSTRACT

Recent breakthrough in mobile technology, wireless communication and sensing ability of smart devices promote the ease to detect real-world learning status of students as well as the context aware for learning. Targeted information can be provided to individual students in the right place and at the right time. This work is one of the three major modules of our Smart Learning Framework, others include Multimedia Module Contents (MMC) and Learning Style Index (LSI). However, this module of our work aimed to perfect efforts to correctly make decision during an academic learning process. This was based on the fact that adaptive decisions can be made to protect learner enthusiasm, promote learning grid and enhances general understanding of an adaptive learning environment if user’s immediate behavior and concern is well considered. This approach implements facial expression recognition on a smart phone (Android) using effective SDK. This enables correct detection of facial expression for further understanding of the meaning in a learning environment. The output of this module is used for learners Behavior Analysis which then provide result of general evaluation of individual learner.
Keywords: Active Appearance Model, Adaptive Learning framework, Smart Learning Environment, Multimedia Learning facilities, Facial Expression Recognition, Deep learning

 

 

TABLE OF CONTENTS

 

CERTIFICATION …………………………………..…………………………………………ii
ABSTRACT ……………………………………………………………………………………..v
ACKNOWLEDGEMENTS ……………………………………………………………………. vi
DEDICATION …………………………………………………………………………. vii
LIST OF ACRONYMS …………………………………………………………………………xi
CHAPTER ONE INTRODUCTION ………………………………………………………..1
1.1 Introduction …………………………………………………………………………..1
1.2 Background …………………………………………………………………………..1
1.3 Cognitive Computing And Computer Vision ………………………………………1
1.4 Human Facial Communication ……………………………………………………..2
1.4.1 Facial Image Recognition ……………………………………………………..…2
1.5 Disadvantages of Image Recognition ……………………………………………..3
1.6 Statement Of the Research Problem ………………………………………………3
1.7 Aim And Objectives of The Research ……………………………………………..3
1.8 Justification ……………………………………………………………………………3
1.9 Scope Of Work………………………………………………………………………..3
1.10 Summary ………………………………………………………………………………4
CHAPTER TWO LITERATURE REVIEW …………………………………………………5
2.1 Research Background ………………………………………………………………5
2.2 Adaptive Learning Framework ……………………………………………………..5
2.2.1 Facial Image Recognition ……………………………………………………….6
2.2.2 Facial Expression Recognition …………………………………………………7
2.2.3 Active Appearance Model (AAM) ………………………………………………8
2.2.4 Facial Recognition In Smartphones ……………………………………………8
2.3 Research Gap And Proposed System …………………………………………… 9
2.4 Summary ……………………………………………………………………………..9
CHAPTER THREE RESEARCH DESIGN AND METHODOLOGY ………………………11
3.1 System Feasibility Studies …………………………………………………………11
3.2 Requirement Analysis ………………………………………………………………12
3.3 System Analysis And Research Approach ………………………………………12
3.4 System Diagrams …………………………………………………………………..13
3.5 System Model ………………………………………………………………………13
ix
3.6 System Process Diagram …………………………………………………………. 14
3.7 System Use-case Diagram ………………………………………………………….15
3.8 Android Application Development ………………………………………………….16
3.9 Affectiva SDK …………………………………………………………………………17
3.10 Alternative Design Consideration …………………………………………………..17
3.11 Image Recognition Using Active Appearance Model (AAM) …………………….18
3.12 Summary ………………………………………………………………………………19
CHAPTER FOUR DATA ANALYSIS AND DISCUSSION OF RESULTS .………………20
4.1 Image Model Training ……………………………………………………………….20
4.2 Facial Recognition And Metric Display …………………………………………….20
4.3 Facial Recognition SDK Features ………………………………………………….20
4.4 Class Diagram Of Facial Recognition System Implemented ……………………21
4.5 Input and Output Screens …………………………………………………………..22
4.6 Accuracy Test ………………………………………………………………………..24
4.7 Adaptive Decision In Smart Learning Environment ………………………………25
4.8 Contribution Of the Research ………………………………………………………25
4.9 Summary …………………………………………………………………………….. 25
CHAPTER FIVE ………………………………………………………………………………….26
CHAPTER SIX SUMMARY, CONCLUSION AND RECOMMENDATIONS …………..26
6.1 Summary ……………….……………………………………………………………..26
6.2 Challenges And Lessons Learned …………………………………………………26
6.3 Image Marking With Active Appearance Model (AAM) Tool ……………………26
6.4 Conclusion ……………………………………………………………………………27
6.5 Recommendations And Further Research Work …………………………………27
6.5.1 Active Appearance Model (AAM) Algorithm Implementation in Smartphones ………………………………………………………………………………………27
6.5.2 Cross-platform Implementation Of Facial Expression Recognition …………27
6.5.3 Multiface Recognition …………………………………………………………….27
References ………………………………………………………………………………………28
APPENDICES ……………………………………………………………………………………31

 

CHAPTER ONE

 

INTRODUCTION
1.1 Introduction
This chapter discusses the fundamental aspects of this work. Our motivation, objectives and limitation were clearly described for easy understanding.
1.2 Background
An adaptive learning system refers to an academic environment for teaching, learning, managing courses, and storing user data; which helps in a better understanding of the user’s learning behaviour and preferences. More importantly, it applies the user’s data to adapt and personalise the various visible aspects of the system, according to the user. Adaptive learning systems tailor the learner’s experience to suit individual needs. The adaptive learning frameworks provide an environment where adaptation and customization are achieved, in order to improve the learning process. Generally, the adaptive learning framework extends and includes the benefits derived from the traditional Learning Management Systems (LMS); and learner personalized support in a distance learning setting.
1.3 Cognitive Computing and Computer Vision
Cognitive computing (CC) describes technology platforms that, broadly speaking, are based on the scientific disciplines of Artificial Intelligence (AI), and image and signal processing. These platforms encompass machine learning, reasoning, natural language processing, speech and vision recognition (Object Recognition), and human-computer interaction. Computer vision (CV) is an interdisciplinary field that deals with how computers can be formulated to gain high-level understanding from digital images or videos; tasks include methods for acquiring, processing, analysing and understanding digital images, and extraction of high-dimensional data from the real-world in order to produce numerical or symbolic information.
2
1.4 Human Facial Communication
Conversation is a form of communication that involves both verbal, or spoken, and nonverbal, or unspoken, ways of ensuring our message is passed from one person to another. When communicating nonverbally with others, we often use facial expressions, which are subtle signals of the larger communication process. Facial expressions include smiling, frowning, eye rolling, making eye contact, scowling etc. in order to pass a nonverbal message (Vasani et al., 2013).
I.Facial Image Recognition
The importance of the facial expression system is widely recognized in social interaction and social intelligence. The system analysis has been an active research topic since the 19th century. The facial expression recognition system was introduced in 1978 by Suwa et al. The main issue of building a facial expression recognition system is face detection and alignment, image normalization, feature extraction, and classification. There are a number of techniques used for recognizing facial expression, including, template matching, and appearance-based methods like Eigenface-based Active Appearance Model, etc. [1-3].
Platform facial expression systems are often designed to work in embedded computers, due to recent development in technology, smartphones can now analyse images and understand the expression in them, within a reasonably short time period.
Several image recognition systems exist in desktop platforms; however, our focus in this research effort is to implement facial expression recognition in mobile smartphone technology.
There is a concern for the security of the data for the Image Recognition System (IRS), with technology advancements. Necessary measures need to be taken to avoid any form of attack and solutions from the active research need to be implemented, e.g., safe transfer of information.
3
1.5 Challenges in Image Recognition
Image recognition, generally, faces a number of problems in implementation, some of these issues, as discussed by other researchers, are broadly; computer resources (memory), speed, accuracy, hard coded solution (non-generic), etc.
1.6 Statement of the Research Problem
An adaptive learning framework can be used to make decisions, by considering not only what a user inputs or clicks but also should identify how a user feels about the learning process. In order to effectively achieve this, a human face is recognized using the front end of a camera of a mobile smartphone and then extract the expression on the face. This can help the smart learning system make more effective decisions in order to ensure that effective learning is not jeopardized.
1.7 Aim and Objectives of the Research
The aim of this research is to design an optimized facial expression recognition application for Android smartphone:
To provide adaptive support to learners through immediate evaluation.
To protect learners’ enthusiasm.
To provide personalized feedback to learners.
1.8 Justification
The success story of mobile technology has made it possible to extract important facial image features for expression recognition in real-time.
Considering the portability, our system aims to exploit a few advantages provided by recent mobile technology success in speed and resources, to name a few.
1.9 Scope of Work
This work is focused on designing effective facial expression recognition on smart mobile smartphones. Six expressions namely: joy, sad, disgust, angry, fear, surprise is recognized by
4
the system. This module is directed to cover the adaptive learning processes of a student by making adaptive decisions based on the recognized learners’ facial expression. In view of this, the mobile application captures the facial image of a learner for extraction, it then analyses it to see what expression is shown in the facial image. This process ensures an efficient conditional decision-making scenario during learning called adaptive learning.
1.10 Summary
In this chapter, we provided a general introduction of what this research effort is all about. We explain the relevance of human emotion in communication, and the security concern and current issues of facial expression recognition. Our direct concern in this study is to design an improved facial recognition system in smartphones. In view of this, a system model has been proposed and provides a detailed explanation of how the research problem was designed and implemented, this is available in the next chapters.

GET THE FULL WORK

DISCLAIMER: All project works, files and documents posted on this website, projects.ng are the property/copyright of their respective owners. They are for research reference/guidance purposes only and the works are crowd-sourced. Please don’t submit someone’s work as your own to avoid plagiarism and its consequences. Most of the project works are provided by the schools' libraries to help in guiding students on their research. Use it as a guidance purpose only and not copy the work word for word (verbatim). If you see your work posted here, and you want it to be removed/credited, please call us on +2348157165603 or send us a mail together with the web address link to the work, to hello@projects.ng. We will reply to and honor every request. Please notice it may take up to 24 or 48 hours to process your request.