Project – Design and implementation of face detection and recognition system

CHAPTER ONE

INTRODUCTION

1.1    Background to the Study

The searches to identify human faces accurately from existing image frame and the specific individuals to which they belong was already well underway and have reached to a new level in research and development in this modern era. In 2019, Google’s famous X laboratory announced their achievement in facial recognition, which has amazed the world (Google, 2019).

In modern day facial recognition, software’s are able to detect by a critical threshold of resemblance among sample image and example patterns, a direct detection is generally declared.

These sorts of modeling have led to detection of facial features such as eyes, mouth, and nose to find out quite easy. However, when it comes to identifying entire face of a person from multiple photograph, analysis is quite complex. In spite of the fact that many improvement has been done in area of face detection and recognition for security, recognizable proof and participation reason, yet there are issues upsetting the advancement to reach or outperform human level exactness. These issues are varieties in human facial appearance, for example, fluctuating lighting condition, clamor in face images, pose, expression and so forth. In this paper, we propose an innovative combination of methods employing SVM Joachims, (2020) combined with HOG (Dalal and Triggs 2019) and KNN (Imandoust and Bolandraftar 2019) to address a portion of the issues obstructing face recognition accuracy in order to improve the widespread face detection and recognition framework.

Face detection and recognition technology is an integral part of today’s technological world. It is not only used in the security sector but also in various other sectors, such as health, education, and agriculture, upstream and downstream. Although some may argue that it invades privacy, people cannot overlook its benefits. The first step in any face recognition system is face detection. It is a process that seeks out human faces in digital images. Despite its simplicity, it plays an essential role in the face recognition system. Face detection algorithms are usually based on machine learning. They are trained on a vast number of positive and negative images. The positive images contain faces, while the negative images do not. After the training, the algorithm can differentiate between images with faces and those without. Face recognition has obtained an increasing amount of attention in machine learning and computer vision over the past few years. The reason is that face recognition technology can be applied in a wide range of fields, such as identity authentication, access control and so on (Chellappa, et al. 2021)

Face detection involves identifying a person’s face in an image or video. This is done by analyzing the visual input to determine whether a person’s facial features are present. Since human faces are so diverse, face detection models typically need to be trained on large amounts of input data for them to be accurate. The training dataset must contain a sufficient representation of people who come from different backgrounds, genders, and cultures. These algorithms also need to be fed many training samples comprising different lighting, angles, and orientations to make correct predictions in real-world scenarios. Generally speaking, there are two categories of methods in face recognition (Ranganath and Arun 2020). One approach is based on facial feature. Firstly, the features such as eyes, nose and mouth first are located and then various feature extraction methods can be adopted to construct feature vectors of these facial features. Finally, traditional pattern recognition methods like a neural network can be used to recognize the feature vectors.

Following face detection is the face recognition process. It involves identifying a person based on their facial features. This process works by comparing the detected face with faces in a database. Firstly, the face detection process identifies a face in an image. After that, the face recognition system captures the facial features. These features are then compared with the features in the database. If a match is found, the face is recognized. Face detection and recognition are used in a variety of sector. It is used in surveillance cameras to identify criminals. It also helps in securing devices by using face recognition as a password. It is used to tag people in photos. It helps in making social media platforms more user-friendly. Companies use it to identify customer’s reactions to their products. It helps companies understand their customer’s behavior.

Despite its numerous benefits, the face detection and recognition system face some challenges. The system might not work effectively in poor lighting conditions. It may not recognize faces with shadows. Different facial expressions can affect the face recognition process. The system might find it hard to recognize faces with different expressions.

In the military as well as commercial fields, facial recognition has been deemed as a popular research area (Kantarc and Ekenel 2019). By evaluating along with relating patterns grounded on a person’s facial features, the person’s identity is verified or identified by utilizing a technique termed facial recognition (Khan, et al. 2019; Murugesh, 2021).

In a real-world scenario, various factors like proxy via pictures, lighting conditions, and lower-quality image processing are the limitations faced by facial recognition algorithms (Harikrishnan, et al. 2019). Moreover, facial recognition turns into a complicated task with the factors like the partial or total occlusion with other objects, the view angle owing to the camera position, or lower-resolution sensors of the obtained image (Cardenas, et al. 2019; Murugesh, 2019). For humans, Facial Recognition is extremely effortless; however, it is distinctive for a machine (Manna, et al. 2020).

1.2    Statement of the Problem

Security is essential in human existence, as such should be taking serious. Every organization is conscious of security and the management of organization go a long way to protect their files, information and property of the organization. In the realm of face detection and recognition system, the statement of the problem revolves around a few key issues. First and foremost is accuracy. Despite significant advancements, the accuracy of face detection and recognition systems is not at 100%. False positives, where the system incorrectly identifies a face, and false negatives, where the system fails to recognize a face, are still prevalent. Moreover, the system’s ability to function effectively under varying conditions is another problem. For instance, changes in lighting, angles, and facial expressions can throw off these systems. Consequently, the robustness of these systems to such variations is still a matter of concern. Based on these assertions, the researcher chooses to design and implement a face detection and recognition system.

1.3    Aim and Objectives of the Study

The aim of the study is to design and implement face detection and recognition system. While the specific objectives are;

1. To design a system that understand the basic principles of face detection and face recognition.
2. To build a system that explore the different techniques and algorithms employed in these system.
3. To implement a system that identifies various applications and practical uses of this system.
4. To test and examine the limitations and challenges faced by this technology

1.4    Significance of the Study

Understanding this technology’s significance is crucial. It is not merely about identifying faces but has much larger implications which include;

Enhancing Security: Face detection and recognition systems play a vital role in enhancing security. Their application in biometric security systems is a testament to this fact. They provide a non-contact process that is hard to fool, thereby improving security.

Streamlining Operations: These systems help streamline operations. For instance, in areas such as surveillance and monitoring, they reduce human intervention. Hence, they make the process more efficient and less prone to errors.

Personalizing User Experience: In the realm of marketing and retail, these systems help personalize user experience. They can identify customer demographics, enabling businesses to tailor their services accordingly.

1.5    Scope of the Study

The scope of this study covers the design and implementation of a face detection and recognition system. it also extends to face detection and face recognition for security access.

 

1.6    Limitations of the Study

The followings are some limitation to this study:

1. Poor lighting Factor: Poor lighting can affect the system’s ability to detect faces accurately. Additionally, a change in pose or expression can also impact its ability to recognize faces.
2. Lack of face for identity: If the database does not have the face to be recognized, the system will not be able to identify it. Therefore, the database needs to be updated regularly.
3. Lack of Fund: There was paucity of fund. A lot of fund was involved to gather data. However, the research was able to make judicious use of the available data in order to conclude the research.

 

 1.7   Project Layout

The project layout for this research are chapter one which discussed the introduction and background to the study, chapter two discussed the literature review, chapter three explained the system analysis and design of the program, chapter four explained  the system implementation and chapter had the summary, conclusion, recommendations, contribution to knowledge and Suggestions for further studies.

1.8    Definition of Terms

Information: is the imaging captured by the database.

Imaging: it is defined as object captured for identification

Identification: this refers to identifying certain object in the database as in form of an image.

System: this is the collection of different parts that is functional.

Imaging System: this refers to a system that captures images or object.

Face Recognition: It seen as a way of identifying or confirming an individual’s identity using their face.

Face Detection: It is defined as an artificial intelligence (AI)-based computer technology used to find and identify human faces in digital form.

Project – Design and implementation of face detection and recognition system