Face Recognition for Real Time Application

Table of Contents

CHAPTER 1: INTRODUCTION

1.1 Background

1.2 Motivation & Objective

1.2.1 Motivation

1.2.2 Problem Statement

1.2.3 Objective

1.3 Software Used

1.3.1 Open-CV

1.4 Database

1.4.1 Olivetti - Att – ORL [40]

1.4.2 The FERET Database, USA

1.5 Scope of Thesis

1.6 Organization of Thesis

2 FACE RECOGNITION SYSTEM

2.1 Face Recognition System

2.1.1 Face Recognition System Classification

2.1.2 Parameters of Face Recognition System

2.2 Real Time Face Recognition System

2.3 Real Time Face Recognition Model

2.3.1 Face Detection

2.3.2 Face Preprocessing

2.3.3 Feature Extraction

2.3.4 Feature Matching

2.4 Face Recognition Task

2.5 Dimension Reduction Technique Used

2.6 Problem & Challenges faced by Face Recognition System

2.7 Applications of Face Recognition System

2.7.1 Government Use

2.7.2 Commercial Use

3 LITERATURE SURVEY

3.1 Introduction

3.2 Literature Review

3.2.1 Comparison between Dimension Reduction Techniques

3.2.2 Summary of various papers

3.3 Literature Gap

3.4 Objective of Present Study

4 DIMENSION REDUCTION TECHNIQUES

4.1 Local Binary Pattern (LBP)

4.1.1 Overview

4.1.2 How LBP Works?

4.1.3 Properties of LBP

4.2 LBP Operator

4.3 Flow Chart of LBP Process

4.4 Face description using LBP

4.5 LBP Applications

5 RESULTS AND DISCUSSIONS

5.1 LBP Circular Histogram

5.1.1 Flow Chart of LBP Circular Histogram Process

5.2 Database Creation

5.3 LBP Frames

5.3.2 LBP 8-bit frame

Features:

5.4 Optimised System

5.5 Maximum Likelihood Prediction

5.6 Results

5.7 Overcome of My Problem Statement

5.8 Limitation

6 CONCLUSION & FUTURE SCOPE

6.1 Conclusion

6.2 Future Scope

Research Objectives and Focus Areas

The primary objective of this thesis is to develop an efficient, real-time face recognition system using the Local Binary Pattern (LBP) algorithm with OpenCV to achieve both low recognition time and high accuracy.

• Enhancement of the frame-per-second (fps) rate to ensure real-time performance.
• Comprehensive study and comparison of different LBP frame bit-rates (8-bit, 10-bit, 16-bit).
• Implementation of a custom face database to optimize performance in high-resolution settings.
• Introduction of a "Maximum Likelihood Prediction" loop to minimize false negatives and boost overall system confidence.
• Optimization of LBP-based feature extraction for robust face representation.

Auszug aus dem Buch

Summary of Chapters

CHAPTER 1: INTRODUCTION: This chapter provides the research motivation, problem statement, and objectives, while introducing the software used and the scope of the thesis.

2 FACE RECOGNITION SYSTEM: An overview of face recognition concepts, applications in real-time, and a classification of face detection and identification methodologies.

3 LITERATURE SURVEY: A detailed review of existing research in face recognition, including various dimension reduction techniques and their performance.

4 DIMENSION REDUCTION TECHNIQUES: Explains the theoretical foundation of the Local Binary Pattern (LBP) operator, its properties, and how it is applied to face description.

5 RESULTS AND DISCUSSIONS: Presents the implementation of the proposed system, including database creation, evaluation of different LBP frame sizes, and the introduction of the Maximum Likelihood Prediction method.

6 CONCLUSION & FUTURE SCOPE: Summarizes the research findings and discusses potential future improvements for the LBP-based real-time face recognition system.

Keywords

Face Recognition, Local Binary Pattern, LBP, Real-Time Systems, Biometrics, Image Processing, OpenCV, Dimension Reduction, Feature Extraction, Face Detection, Maximum Likelihood Prediction, Pattern Recognition, Texture Analysis, Surveillance, Database Registration.

Frequently Asked Questions

What is the core focus of this research?

The research focuses on creating an efficient face recognition system for real-time applications that balances high accuracy with low processing time using the Local Binary Pattern algorithm.

What are the primary thematic areas covered?

The thesis covers face recognition methodologies, feature extraction using LBP, real-time image processing, dimension reduction techniques, and performance benchmarking for different LBP frame configurations.

What is the main objective or research question?

The main objective is to reduce the computational time required for face recognition to enable real-time operation while maintaining high accuracy in high-resolution video streams.

Which scientific methodology is primarily used?

The study utilizes the Local Binary Pattern (LBP) operator as the primary texture descriptor and dimension reduction technique, implemented via OpenCV on a Linux platform.

What does the main body of the work address?

The main body covers the theoretical background of face recognition, a comprehensive survey of literature, detailed descriptions of LBP variations (16-bit, 8-bit, 10-bit), and the development of a custom face database.

Which keywords best characterize this work?

The key terms include Face Recognition, Local Binary Pattern (LBP), Real-Time Processing, Biometrics, and Maximum Likelihood Prediction.

How does the "Maximum Likelihood Prediction" loop function?

It is a post-processing step that analyzes three consecutive predictions; it provides a high-confidence result only if all three match, significantly reducing false negatives in security-sensitive scenarios.

Why are different LBP frame bit-rates compared?

The study compares them to determine the optimal trade-off between speed and accuracy, finding that different bit-rates influence confidence levels and processing time differently.

What were the major limitations identified in the study?

The system's performance currently degrades under varying or non-optimal lighting conditions, which the author suggests can be addressed through better hardware light sources in future iterations.