reunite (1)

An Industry Oriented Mini Project (CS705PC)
on
REUNITE USING FACE RECOGNITION
by
B .Kirthi priya(22265A6607)
Under the Guidance of
GUIDE NAME
(Dr . Jesalkumari Joshi)
Department of Computer Science and Engineering

MAHATMA GANDHI INSTITUTE OF TECHNOLOGY
Abstract
In countries with vast populations and frequent public gatherings, issues like individuals
getting separated from their peers, particularly children getting separated from their
families, often arise. This can be challenging even to the police, who struggle to locate
missing persons through manual searches. Although Cyber departments use software to
search databases and CCTV footage for reported missing cases, the process remains time-
consuming and sometimes inaccurate. To overcome this situation and make this searching
process easier, we make use of people to help people. We build a common portal which is
accessible by both people who lost someone and those who found someone they think is
lost. The portal accepts images , features and last seen location of missing person and
stores it in a database. Also the public can upload photographs of the supposedly found
person along with their landmarks and remarks. The photo will be automatically
compared with the registered photos of the missing person from the repository.
Classification of the input image is performed and image with best match will be
retrieved from the database. For this, a deep learning model is trained to correctly identify
the facial features. Another major addition is that this model is invariant to noise, contrast
and even the age of the person.
Introduction
Reunite is an innovative application leveraging face recognition technology to help
reconnect lost individuals with their families. By using advanced AI algorithms, the
system accurately matches missing persons with their loved ones through facial
feature analysis. This solution is designed to assist in humanitarian efforts,
streamline search processes, and enhance safety by bridging gaps between separated
individuals, whether due to natural disasters, accidents, or other circumstances. With
a focus on privacy and security, Reunite ensures efficient, ethical, and secure
handling of sensitive information while aiming to bring families back together. The
process includes uploading the image and last seen details by the family member.
This will be stored in the database and it will be used for further comparison when
somebody (A police or any other citizen) who uploads the image of a reportedly
missing person. After performing the face matching if any match is found then the
present details of the missing person will be sent to their family. To achieve this our
model uses the help of ML image processing models.
Existing System
• The current search process has limited resources and relies heavily on manual
efforts.
• The process lacks coordination, and communication between the parties involved
is often delayed.
• Although Cyber departments use software to search databases and CCTV footage
for reported missing cases, the process remains time-consuming and sometimes
inaccurate.
Proposed System
• REUNITE uses the latest algorithms to provide real-time search results.
• REUNITE connects missing person reports with volunteers, agencies, and families
to quickly mobilize search teams.
• REUNITE provides instant messaging and updates to ease communication and
coordination between parties involved in the search process.
• REUNITE provides 24/7 support to help families, law enforcement, and volunteers
find missing persons quickly and efficiently.
• REUNITE incorporates a centralized online platform and machine learning
technology to facilitate accurate identification and reunification.
• An easily accessible online portal serves as the primary interface for reporting
missing persons.
Technical Specification
Software Requirements
• Website: Frontend Development- HTML5 CSS3 (for styling) JavaScript (for interactive features) Frameworks
like React, Angular, or Vue.js for a dynamic user interface.
• Backend Development: Node.js, Python, or another suitable backend language. Express.js (for Node.js) or
Flask/Django (for Python) for web server development.
• Database: MongoDB, MySQL for storing relevant data.
Hardware Requirements
• Server:
CPU : 2x Intel Xeon E5-2620 v4 or AMD EPYC 7401
Memory : 64GB RAM
Storage : 1TB SSD ,Network : 10Gbps Ethernet. 8
• Client:
CPU: 2x Intel Xeon E5-2620 v4 or AMD EPYC 7401
Memory : 64GB RAM
Storage : 1TB SSD ,Network : 10Gbps Ethernet.
Conclusion
Reuniting people utilizing a machine learning model for facial recognition and a
centralized lost and found portal, offers a promising solution to the issue of missing
persons in crowded environments. Its combination of image and feature
registration, public image uploading, automated image comparison, noise-invariant
and contrast-adaptive recognition, and deep learning model training enables
efficient and accurate matching, leading to timely reunions. The system’s scalability
and accessibility further enhance its potential for real-world implementation,
making it a valuable tool for addressing this critical societal concern.
Bibliography
[1] Face Detection in Extreme Conditions: A Machine-learning Approach Sameer
Aqib Hashmi Department of Electrical and Computer Engineering North South
University, Bashundhara Dhaka, Bangladesh.
[2] Retracted: Intelligent Face Recognition System Based on Universal Design

Concept Computational Intelligence and Neuroscience
[3] MISSING PERSON IDENTIFICATION USING FACE RECOGNITION Mr. E.

Murali*1, S. Achyuth*2, V. Nithya Sree*3, B. Dilli Kavitha*4, R. Raj Kumar*5, M.
Vedhardhi*6

reunite (1)

Uploaded by

Copyright:

Available Formats

reunite (1)

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

reunite (1)

Uploaded by

Copyright:

Available Formats

An Industry Oriented Mini Project (CS705PC)

REUNITE USING FACE RECOGNITION

Under the Guidance of

Department of Computer Science and Engineering

[2] Retracted: Intelligent Face Recognition System Based on Universal Design

[3] MISSING PERSON IDENTIFICATION USING FACE RECOGNITION Mr. E.

You might also like