A Seminar Report on

TITLE OF THE SEMINAR IN CAPITAL LETTERS

Submitted in partial fulfilment of the requirements
for the award of the degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
By

STUDENT NAME (21UJ1A05XX)

Under the esteemed guidance of

Mrs.XXXXXXX M.Tech.
Assistant Professor
Department of Computer Science and Engineering

At

MALLA REDDY ENGINEERING COLLEGE AND

MANAGEMENT SCIENCES
Kistapur (V), Medchal (M), Medchal Malkajgiri (Dist)-
501401.
(An UGC autonomous Institution, NBA Accredited in CSE, ECE, IT, EEE)
.
2025
Affiliated to

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD

KUKATPALLY, HYDERABAD-85.
 MALLA REDDY ENGINEERING COLLEGE AND
MANAGEMENT SCIENCES
Kistapur (V), Medchal (M), Medchal Malkajgiri (Dist)-
501401.
(An UGC autonomous Institution, NBA Accredited in CSE, ECE, IT, EEE)

CERTIFCATE

This is to certify that the Seminar report entitled “ SEMINAR TITLE “is the
bonafide work carried out and submitted by

STUDENT NAME (21UJ1A05XX)

To the department of Computer Science and Engineering, Malla Redddy Engineering College
and Management Sciences, in partial fulfilment for the award of BACHELOR OF

TECHNOLOGY IN COMPUTER SCIENCE AND ENGINEERING during the academic year

202024-2025.

Internal Guide Head of The Department

Mrs.XXXXXXXXM.Tech. Dr.P.PRASHANTHI M.Tech.,PhD,..
Assistant Professor Assistant Professor
Dept. of Computer Science and Engineering Dept. of Computer Science and Engineering
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompany the successful completion of any task would
be incomplete without the mention of people who made it possible, whose constant guidance and
encouragement crowned our efforts with success. It is a pleasant aspect that I have now the
opportunity to express my guidance for all of them.

I am thankful to Mr.V.MALLA REDDY chairman of Malla Reddy Engineering College

and Management Sciences for accepting me and providing me with an opportunity to do a project in
their esteemed organization.

I thankful to Principal Dr.M.SREEDHAR REDDY M.Tech., Ph.D. Malla Reddy Engineering

College and Management Sciences for helped me to undergo project work as a part of university
curriculum.

My special thanks to Dr.P.PRASHANTHI M.Tech., Ph.D. Assistant Professor & Head in

Computer Science and Engineering Department and Mrs. <<INTERNAL GUIDE>> M.Tech.

Assistant Professor in Computer Science and Engineering Department for guiding me in the right
way to complete my project in the right time.

We would like to thank our internal project mates and department faculties for their
full-fledged guidance and giving courage to carry out the project.

I am very much thankful to one and all that helped me for the successful completion of my project.

STUDENT NAME (21UJ1A05XX)

 t

List Of Figures
Figure No. Title Description
Overview of the
Illustrates the general workflow of an image recognition
1 Image Recognition
system, from image input to prediction.
Pipeline

Convolutional
Shows the structure of a CNN with layers like convolutional,
2 Neural Network
pooling, and fully connected layers.
(CNN) Architecture

Example of Object Displays the process of detecting objects within images using
3
Detection algorithms like YOLO or R-CNN.

Training Process for

A diagram illustrating the training process, from data
4 Image Recognition
preparation to model optimization.
Models

Image Preprocessing Visualizes preprocessing steps like resizing, normalization,

5
Techniques and augmentation applied to input images.

Feature Extraction Shows the process of extracting features from images using
6
Process methods like HOG, SIFT, or CNN.

A bar graph or chart comparing the accuracy or performance of

7
different recognition models.
 Abbreviations
Abbreviation Full Form Description
The simulation of human intelligence in
AI Artificial Intelligence
machines.

A subset of AI focused on systems that learn

ML Machine Learning
from data.

A subset of ML using neural networks with

DL Deep Learning
many layers for advanced analysis.

A deep learning architecture designed for image

CNN Convolutional Neural Network
data analysis.

A type of neural network useful for sequential

RNN Recurrent Neural Network
data but occasionally used in image recognition.

A type of neural network used to generate

GAN Generative Adversarial Network
images and improve image quality.

A feature extraction method used in image

HOG Histogram of Oriented Gradients
recognition.

Scale-Invariant Feature A method for detecting and describing local

SIFT
Transform features in images.

A dimensionality reduction technique often used

PCA Principal Component Analysis
in image recognition.

IoU Intersection over Union A metric for evaluating object detection models.

An object detection algorithm for real-time

SSD Single Shot MultiBox Detector
applications.

YOLO You Only Look Once A popular real-time object detection algorithm.

Region-based A family of object detection

R-CNN Convolutional Neural algorithms (e.g., Fast R-CNN,
Network Faster R-CNN).
Multi-task Cascaded Used for face detection and
MTCNN
Convolutional Networks alignment.
DNN Deep Neural Network Neural networks with multiple
layers, commonly used in image
Abbreviation Full Form Description

recognition.
Specialized hardware developed by
TPU Tensor Processing Unit Google for accelerating deep
learning tasks.
Graphics Processing Hardware used for processing large-
GPU
Unit scale image and video data.
A large-scale dataset used for image
Common Objects in
COCO recognition and object detection
Context
tasks.
A network of interconnected
IoT Internet of Things devices, often leveraging image
recognition.

Nomenclature
Algorithms and Models
 Convolutional Neural Network (CNN): A type of neural network specifically designed for
image data.

 Generative Adversarial Artificial Intelligence (AI): Simulating human intelligence in

machines, encompassing image recognition.

 Machine Learning (ML): Algorithms that allow systems to learn patterns in image data.

 Deep Learning (DL): A subset of ML that uses neural networks with many layers for image
analysis.

 Network (GAN): Used for generating or enhancing images.

 Region-based Convolutional Neural Network (R-CNN): Popular object detection models

(e.g., Fast R-CNN, Faster R-CNN).

 You Only Look Once (YOLO): A real-time object detection algorithm.

 Single Shot Detector (SSD): Another real-time object detection algorithm.

 Transformer Models: Emerging architectures like Vision Transformers (ViTs) for image
recognition.

Data Processing

 Feature Extraction: Techniques like Histogram of Oriented Gradients (HOG) or Scale-

Invariant Feature Transform (SIFT).

 Dimensionality Reduction: Methods like Principal Component Analysis (PCA) to reduce

data complexity.

 Preprocessing: Steps such as normalization, resizing, and augmentation to prepare image

data.

Metrics

 Accuracy: Percentage of correctly classified images.

 Precision: Correctly predicted positive samples divided by all predicted positives.

 Recall: Correctly predicted positives divided by all actual positives.

 F1-Score: The harmonic mean of precision and recall.

 Intersection over Union (IoU): A measure used in object detection to evaluate bounding
box overlap.

Datasets
  ImageNet: A large-scale dataset for image classification tasks.

 COCO (Common Objects in Context): A dataset for object detection, segmentation, and
captioning.

 CIFAR-10/CIFAR-100: Small datasets often used for benchmarking image recognition

models.

 MNIST: Dataset of handwritten digits, often used for beginner-level tasks.

Hardware

 Graphics Processing Unit (GPU): Accelerates the training of large-scale image recognition
models.

 Tensor Processing Unit (TPU): Specialized hardware for deep learning tasks.

 Edge Devices: Devices like smartphones and IoT devices capable of running image
recognition algorithms.
 INTRODUCTION
Face recognition technology is a biometric innovation that identifies and verifies individuals by
analyzing their facial features. It has emerged as one of the most advanced and widely adopted tools
in the field of artificial intelligence and computer vision. This technology mimics the human ability
to recognize faces but with enhanced speed, accuracy, and scalability. By extracting unique features
such as the distance between eyes, nose shape, and jawline structure, face recognition systems can
compare these attributes against stored data to identify or authenticate a person.

In recent years, face recognition has gained immense popularity due to its seamless, contactless
operation and broad range of applications. From enhancing security in public spaces and enabling
facial unlock in smartphones to providing personalized user experiences in retail and marketing, its
use cases span across various industries. As society continues to integrate face recognition
technology into daily life, it holds the potential to redefine how humans interact with digital
systems, making security and convenience more accessible than ever. However, its rapid adoption
also raises ethical, legal, and privacy concerns that demand careful attention and regulation .

ace recognition technology operates through a series of sophisticated steps, beginning with face
detection, where the system identifies the presence of a face in an image or video. This is followed
by feature extraction, which involves analyzing distinct facial landmarks, such as the eyes, nose,
and mouth, to create a unique biometric template for each individual. These templates are then
compared against a database of stored faces using advanced algorithms, such as convolutional
neural networks (CNNs), to identify or verify a person. The integration of deep learning has
significantly enhanced the accuracy and efficiency of these systems, making them reliable for both
real-time and large-scale applications.

Despite its advantages, the growing use of face recognition technology has sparked debates
surrounding privacy and ethical implications. Concerns about unauthorized data collection,
surveillance, and algorithmic biases have become prominent as the technology expands its reach.
Misidentifications due to poorly trained models or biased datasets can lead to unfair treatment,
particularly for underrepresented demographics. To address these challenges, it is essential to invest
in the development of inclusive algorithms, establish transparent policies, and enforce robust
privacy regulations. By addressing these concerns, face recognition technology can be utilized
responsibly, ensuring it benefits society while respecting individual rights.
 LITERATURE SURVEY

Face recognition technology has been an area of extensive research and development over the past
few decades. Early studies primarily focused on geometric approaches, such as the analysis of facial
landmarks and template matching techniques. For instance, Kanade (1973) introduced one of the
first automated systems for face recognition using manually extracted features. This was a
pioneering attempt but limited by the lack of computational power and robust algorithms.

The advent of statistical methods marked a significant improvement in the field. Turk and
Pentland (1991) introduced the Eigenfaces method, which used principal component analysis
(PCA) to represent faces as a combination of basis features. This approach laid the foundation for
modern face recognition by demonstrating the potential of dimensionality reduction techniques.
However, it was sensitive to variations in lighting and pose, which restricted its practical
applications.

In the 2000s, the rise of machine learning and support vector machines (SVMs) provided more
powerful classification methods. Belhumeur et al. (1997) proposed Fisherfaces, an improvement
over Eigenfaces, by using linear discriminant analysis (LDA) to achieve better class separability.
Although these approaches were successful in controlled environments, real-world challenges like
occlusions and dynamic conditions remained unsolved.

The introduction of deep learning in the 2010s revolutionized face recognition systems. Taigman et
al. (2014) introduced DeepFace, one of the first deep learning-based systems developed by
Facebook. It used convolutional neural networks (CNNs) to achieve near-human-level accuracy.
Similarly, Schroff et al. (2015) proposed FaceNet, which used a triplet loss function to map faces
into a Euclidean space, enabling efficient face comparisons. These advancements allowed face
recognition systems to handle large-scale datasets and real-world variability effectively.

Recent studies have focused on addressing ethical concerns and improving fairness in face
recognition systems. For instance, Buolamwini and Gebru (2018) highlighted biases in
commercial face recognition systems, emphasizing the need for more diverse training datasets.
Additionally, researchers have explored privacy-preserving techniques, such as federated learning
and homomorphic encryption, to mitigate concerns around unauthorized data usage.
ARCHITECTURE
 APPLICATIONS
Image recognition technology has a wide range of applications across various industries. Some of
the key applications include:

1. Healthcare:

o Medical Imaging: Image recognition is used in analyzing medical images like X-

rays, CT scans, MRIs, and ultrasounds to detect diseases such as cancer, tumors,
fractures, or other abnormalities.

o Skin Cancer Detection: Machine learning algorithms analyze images of moles and
skin lesions to classify and detect potential skin cancers, assisting dermatologists in
diagnosis.

2. Security and Surveillance:

o Facial Recognition: Used for identifying individuals from images or video feeds. It
is widely used for access control, law enforcement, and security systems.

o Object Detection: Image recognition systems detect and classify objects in

surveillance footage for monitoring security in public spaces.

3. Autonomous Vehicles:

o Object Detection: Image recognition is used in self-driving cars to detect

pedestrians, road signs, other vehicles, and obstacles for navigation and safety.

4. Retail and E-commerce:

o Product Search: Image recognition allows users to search for products online by
taking pictures, making shopping easier.

o Inventory Management: Helps retailers track products on shelves through image

analysis, streamlining stock management.

5. Agriculture:

o Crop Monitoring: Image recognition technology is used to analyze satellite or

drone images for crop health, pest detection, and yield prediction.

o Weed Identification: Helps farmers identify weeds in fields to improve efficiency in

using herbicides and fertilizers.

6. Manufacturing:

o Quality Control: In manufacturing, image recognition is used to inspect products

for defects and ensure quality during production.

o Robotics: Robots equipped with image recognition capabilities can handle tasks
such as sorting and assembling parts.
 ADVANTAGES
Face recognition technology offers a variety of advantages across different applications. Here are
some of the key benefits:

1. Enhanced Security:

o Accurate Authentication: Face recognition is a reliable method for verifying

identities, making it an effective tool for securing access to physical locations,
devices, or systems. It is harder to forge or spoof than traditional methods like
passwords or PINs.

o Fraud Prevention: In financial services or retail, face recognition can help prevent
fraudulent activities, such as unauthorized transactions or identity theft, by ensuring
the person accessing an account or making a purchase is the legitimate user.

2. Convenience and Speed:

o Contactless Authentication: Unlike fingerprint or iris scanning, face recognition

doesn't require any physical interaction, making it faster and more convenient for
users. It can authenticate individuals without requiring them to stop or touch
anything.

o Quick Identification: Face recognition enables rapid identification, which is

particularly useful in security scenarios, airport check-ins, or crowded events where
manual identification would be too time-consuming.

3. Non-Intrusive:

o Privacy-Friendly: Face recognition is less invasive than other biometric methods,

such as fingerprinting, as it doesn't require physical contact. This makes it more
comfortable for users and can be deployed in public spaces without causing
discomfort.

o Seamless Integration: It can be integrated into existing infrastructure, such as

surveillance cameras or smartphones, without requiring additional hardware.

4. Scalability:

o Large-Scale Deployment: Face recognition systems can handle large numbers of

people, which makes them ideal for applications in airports, stadiums, public
transport, and large-scale events.

o Automated Processing: It can scan and process faces in real-time across large
datasets (e.g., crowd monitoring) without slowing down the system, making it
scalable for enterprise-level applications.

5. Improved User Experience:

o Hands-Free Interaction: Users can access devices, apps, or secure areas simply by
being recognized by the system, improving ease of use and streamlining interactions.
 o Personalization: Face recognition can be used to create personalized experiences,
such as tailored content or services based on the individual’s identity (e.g.,
personalized greetings, offers, or preferences).

6. Enhanced Safety and Monitoring:

o Crime Prevention and Detection: In public security, face recognition can be used
for identifying known criminals, missing persons, or suspects in real-time
surveillance footage, which helps law enforcement agencies quickly act on potential
threats.

o Access Control: In sensitive areas (e.g., government buildings, data centers), face
recognition ensures that only authorized individuals can enter, improving physical
security.

7. Healthcare and Emergency Response:

o Patient Identification: In healthcare, face recognition can be used to confirm patient

identities, reducing errors in medical records and ensuring the correct treatments are
administered.

o Emergency Situations: In situations where an individual is unconscious or

unresponsive, face recognition can help identify the person and alert medical
responders to their medical history, allergies, or other vital information.

8. Retail and Marketing:

o Customer Analytics: Retailers can use face recognition to gauge customer

demographics (age, gender, mood) in real-time, enabling them to tailor marketing
strategies, improve customer service, and enhance the shopping experience.

o Loyalty Programs: Face recognition can be used to identify returning customers,

offering them personalized experiences, discounts, or loyalty rewards.

9. Law Enforcement and Forensics:

o Identifying Criminals and Suspects: Face recognition is used in law enforcement

to match suspects' images against databases of known criminals, helping
investigators track and capture criminals more effectively.

o Evidence Collection: It aids in identifying individuals in video surveillance footage,

potentially linking suspects to criminal activities.

10. Remote Work and Education:

o Attendance Tracking: In both educational institutions and workplaces, face

recognition can be used to automatically track attendance, saving time and reducing
the potential for cheating or falsified records.

o Virtual Access: Face recognition can be integrated into virtual environments or

remote work platforms for secure login and user verification, ensuring that only
authorized individuals can access sensitive online resources.

11. Assistive Technology:

 DISADVANTAGES
Bias and Accuracy Issues While face recognition technology offers numerous benefits, it also
comes with some disadvantages and challenges. Here are some of the key drawbacks:

1. Privacy Concerns:

o Invasion of Privacy: The widespread use of face recognition can lead to concerns
about surveillance and the erosion of personal privacy. People may be constantly
monitored without their knowledge or consent, raising ethical questions about
consent and data ownership.

o Data Security Risks: Face recognition systems store sensitive biometric data, which
could be vulnerable to hacking or misuse if not properly protected. A breach of such
data could have severe consequences, as biometric data is unique and cannot be
changed like passwords.

2. Bias and Accuracy Issues:

o Racial and Gender Bias: Studies have shown that face recognition algorithms can
be biased, often performing less accurately for people of certain races, ethnicities, or
genders. This can result in higher false positive or false negative rates for minority
groups, leading to discrimination or unfair treatment.

o Lower Accuracy in Poor Conditions: Face recognition technology can struggle in

low-light environments, with poor-quality images, or when faces are partially
obscured (e.g., wearing masks, glasses, or hats). This may result in errors, especially
in security and identification applications.

3. Misidentification and False Positives:

o False Identifications: The technology is not perfect, and false positives (incorrectly
identifying someone) or false negatives (failing to identify someone) can occur,
especially when the system is not trained on diverse datasets. This can lead to
wrongful accusations, exclusion from services, or even security breaches.

o Mistaken Identity: In sensitive areas such as law enforcement or immigration,

incorrect identification can have serious consequences, including wrongful arrests or
denial of entry.

4. Dependence on Quality Data:

o Quality of Data Matters: The performance of face recognition algorithms depends

on the quality and resolution of the images they are analyzing. If the system receives
blurry, low-resolution, or distorted images, it may perform poorly, leading to
misidentifications.
 o Data Collection Challenges: Ensuring diverse and representative datasets to train
face recognition systems is a major challenge. Inadequate training data can
negatively impact the system's accuracy and fairness.

5. Ethical and Legal Issues:

o Lack of Regulation: The rapid adoption of face recognition technology has

outpaced legislation and regulation in many countries. There are concerns about how
this technology is being used, who has access to the data, and whether it complies
with data protection laws like GDPR.

o Surveillance State: Widespread use of face recognition by governments and private

organizations can lead to a "surveillance state," where individuals' movements and
activities are constantly tracked. This may infringe on civil liberties, including
freedom of expression and the right to anonymity.

6. Impact on Personal Freedom:

o Loss of Anonymity: Face recognition removes the ability for people to move
through public spaces anonymously, as they can be identified in real time. This could
deter individuals from participating in protests, rallies, or other activities where they
may want to remain unrecognized.

o Social Control: The use of face recognition technology in public spaces could be
used to monitor and control populations, leading to societal pressure or restrictions
on individual behavior.

7. Cost of Implementation:

o Expensive Setup: Implementing face recognition systems can be costly, especially

for organizations that need to upgrade their infrastructure or acquire specialized
hardware (e.g., high-quality cameras, sensors). This could be a barrier to entry for
smaller businesses or institutions.

o Maintenance and Upgrades: The technology requires regular updates and

maintenance to stay current with advancements, which can incur additional costs for
organizations.

8. Over-reliance on Technology:

o False Sense of Security: Over-reliance on face recognition for security purposes

could lead to complacency, where organizations fail to implement additional layers
of security or human oversight. This could leave systems vulnerable if the
technology fails or is bypassed.

o Hackable Systems: While face recognition is generally secure, it is not immune to

hacking. With advancements in AI and deep learning, there are concerns about the
potential for deepfakes or 3D facial models being used to trick face recognition
systems.

9. Psychological and Social Impact:

 o Chilling Effect: The awareness that face recognition is being used widely could
cause individuals to alter their behavior, self-censor.

FUTURE SCOPE
The future scope of face recognition technology is vast, and it is expected to continue evolving
across various domains. Here are some potential directions and innovations for the future of face
recognition:

1. Improved Accuracy and Reliability:

o Higher Precision with AI and Deep Learning: As AI and deep learning algorithms
improve, face recognition systems will become more accurate, even in challenging
conditions like low light, obstructions, or poor-quality images. Algorithms will be
able to better handle diverse facial features, enhancing fairness and reducing bias.

o Multi-modal Authentication: Combining face recognition with other biometric

systems (e.g., fingerprint scanning, voice recognition, or iris scanning) will improve
security and accuracy, providing multi-layered authentication methods for more
robust identity verification.

2. Enhanced Privacy Protections:

o Decentralized and Secure Storage: To address privacy concerns, face recognition

technology may shift to more secure, decentralized storage models where biometric
data is not stored centrally but is encrypted and stored locally on users' devices.

o Privacy-First Design: Future face recognition systems will likely incorporate

privacy-enhancing technologies, such as "privacy by design" features, that give users
more control over how and when their data is used, ensuring compliance with data
protection laws like GDPR.

3. Integration with IoT and Smart Environments:

o Smart Homes and Devices: Face recognition will play a key role in enhancing
smart home devices. It could be used for personalized home automation, allowing
systems to recognize and adjust settings based on who is in the room, such as
lighting, temperature, or entertainment preferences.

o Seamless User Interactions: Face recognition will be integrated into IoT devices
(e.g., smart speakers, refrigerators, or vehicles), allowing users to interact with their
environment more intuitively. For example, cars may recognize the driver’s face to
unlock and personalize settings automatically.

4. Wider Adoption in Healthcare:

o Personalized Healthcare: Face recognition could be used to monitor patients’

health conditions by detecting changes in facial expressions or subtle physical signs
that indicate pain, fatigue, or illness. For example, analyzing facial cues to detect
early symptoms of conditions like strokes or neurological disorders.
 o Remote Healthcare: Telemedicine and remote healthcare applications could
incorporate face recognition to verify patient identities and enhance the quality of
virtual consultations, improving trust and security in digital healthcare services.

5. Greater Use in Retail and Customer Experience:

o Personalized Retail: Face recognition will enable hyper-personalized shopping

experiences. Stores may be able to recognize returning customers and offer them
tailored product recommendations, personalized discounts, or even customized store
layouts based on their preferences.

o Contactless Payments: Integration of face recognition with payment systems could

allow customers to make secure, contactless transactions simply by having their face
scanned, reducing the need for physical wallets or cards.

6. Improved Law Enforcement and Public Safety:

o Predictive Policing and Crime Prevention: Advanced face recognition systems

could be used to predict and prevent criminal activity by identifying suspicious
individuals or behavior in real-time across large crowds or public spaces. This would
help law enforcement agencies act proactively to prevent incidents before they occur.

o Search and Rescue: Face recognition could be used in search and rescue operations,
helping authorities identify missing persons quickly from images or video footage,
especially in large or complex environments such as natural disaster sites or crowded
public events.

7. Ethical AI and Bias Mitigation:

o Diversity and Inclusion in Training Data: Future face recognition systems will
focus on ensuring that the datasets used for training are more diverse and representative,
reducing biases based on race, gender, age, or other demographic factors. This will lead
to more equitable and fair systems.

o Regulation and Transparency: Governments and organizations will likely

implement more comprehensive regulations to ensure face recognition technologies
are used responsibly, transparently, and ethically. This could include audit trails,
public transparency about how the technology is used, and independent oversight
bodies.

8. AI-Powered Facial Expression Recognition:

o Emotional Intelligence in Machines: Face recognition will evolve to include facial

expression recognition, which could help machines understand human emotions.
This could be useful in areas like customer service (e.g., virtual assistants), mental
health diagnostics, or even gaming, where understanding emotional responses can
enhance user experiences.
 CONCLUSIONS
In this paper, the importance of face recognition and its numerous applications, algorithms,
methods, face databases are discussed. Two major feature extraction methods for face recognition
(Appearance-based and Model-Based). Appearance-Based includes PCA, LDA, ICA, and
ModelBased includes EBGM and 3D Morphable Model. Different feature extraction methods with
its previous work are discussed. Distance Measurement such as Euclidean Distance, City Block, and
Mahalanobis Distance are important for recognition process, the Distance Measurement methods
are discussed. Several face recognition databases are available and can be used to test the sys
 REFERENCES
[1] Jain, A.K. and Li, S.Z., 2011. Handbook of face recognition. New York: springer. [2] Dewi
Agushinta, R. and Septadepi, I., Face Recognition System Using Eigenface Method based on Facial
Component Region. [3] Pornpanomchai, C. and Inkuna, C., 2010, February. Human face
recognition by euclidean distance and neural network. In Second International Conference on
Digital Image Processing. International Society for Optics and Photonics. pp. 754603-754603. [4]
Zhao, W., Chellappa, R., Phillips, P.J. and Rosenfeld, A., 2003. Face recognition: A literature
survey. ACM computing surveys (CSUR), 35(4), pp.399-458. [5] Chellappa, R., Wilson, C.L. and
Sirohey, S., 1995. Human and machine recognition of faces: A survey. Proceedings of the IEEE,
83(5), pp.705-741. [6] Jafri, R. and Arabnia, H.R., 2009. A survey of face recognition
techniques.Jips, 5(2), pp.41-68. [7] Lu, X., 2003. Image analysis for face recognition, personal
notes. Dept. of Computer Science and Engineering. [8] Shah, D.H., Shah, D.J. and Shah, D.T.V.,
2014. The Exploration of Face Recognition Techniques. International Journal of Application or
Innovation in Engg. And Management (IJAIEM) Web Site: www. ijaiem. org Email: editor@
ijaiem. org, editorijaiem@ gmail. com, 3(2). [9] Parmar, D.N. and Mehta, B.B., 2014. Face
Recognition Methods & Applications. arXiv preprint arXiv:1403.0485. [10] Kurmi, U.S., Agrawal,
D. and Baghel, R.K., Study of different face recognition algorithms and challenges. IJER, Volume,
(3), pp.112-115. [11] Kadam, K.D., 2014. Face Recognition using Principal Component Analysis
with DCT. International Journal of Engineering Research and General Science, ISSN, pp.2091-
2730. [12] Slavković, M. and Jevtić, D., 2012. Face recognition using eigenface approach. Serbian
Journal of Electrical Engineering, 9(1), pp.121-130. [13] Sharma, N. and Dubey, 2014. A.P.S.K.,
Face Recognition Analysis Using PCA, ICA And Neural Network. International Journal of Digital
Application & Contemporary research, 2(9). [14] Murtaza, M., Sharif, M., Raza, M. and Shah, J.,
2014. Face recognition using adaptive margin fisher’s criterion and linear discriminant
analysis.International Arab Journal of Information Technology, 11(2), pp.1-11. [15] Sahu, R.K.,
Singh, Y.P. and Kulshrestha, A., 2013. A Comparative Study of Face Recognition System Using
PCA and LDA. International Journal of IT, Engineering and Applied Sciences Research, 2(10). [16]
Christry, C., Pavithra, J. and Sathya, F.M., 2014. Comparison on PCA ICA and LDA in Face
Recognition. International Journal of Computing Algorithm,3, pp.917-922. [17] Naik, G.R. and
Kumar, D.K., 2011. An overview of independent component analysis and its applications.
Informatica, 35(1). [18] Wang, L., Zhang, Y. and Feng, J., 2005. On the Euclidean distance of
images. IEEE transactions on pattern analysis and machine intelligence, 27(8), pp.1334-1339. [19]
Taghizadegan, Y., Ghassemian, H. and NaserMoghaddasi, M., 2012. 3D Face Recognition Method
Using 2DPCA-Euclidean Distance Classification.ACEEE International Journal on Control System
and Instrumentation, 3(1). [20] Barnouti, N.H., 2016. Improve Face Recognition Rate Using
Different Image Pre-Processing Techniques. American Journal of Engineering Research (AJER),
5(4), pp. 46-53. [21] Kapoor, S., Khanna, S. and Bhatia, R., 2010. Facial gesture recognition using
correlation and mahalanobis distance. arXiv preprint arXiv:1003.1819. [22] Gawande, M. P., and
Agrawal, D. G., 2014. Face recognition using PCA and different distance classifiers. IOSR Journal
of Electronics and Communication Engineering (IOSR-JECE), 9(1), pp. 1-5. [23] Abdullah, M.,
Wazzan, M.