BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE ENGINEERING
6th Semester
SYNOPSIS
ON
FindAI
Submitted to:
1
INDEX
Contents Page No.
1. Introduction 3
2. Objective 4
3. Tools and Platform 5
4. Hardware and Software Requirement 6
5. Data Flow Diagram 7
6. Modules 8
7. Future Scope 9
8. Reference 10
2
INTRODUCTION
Finding Missing Person using AI is an innovative solution designed to assist law
enforcement agencies and families in locating missing individuals efficiently. The system
leverages Artificial Intelligence, Face Recognition, Machine Learning, and Cloud
Databases to analyze CCTV footage, social media, and public records.
Unlike traditional manual search methods, this system automates identification and
tracking, reducing the time and effort required to locate a missing person. The aim is to
provide a reliable, fast, and technology-driven solution for missing person investigations.
Moreover, AI can assist in predictive analysis, identifying potential locations where the
person might be based on historical data, social connections, and geographic patterns.
Integration of AI with mobile apps and public platforms also allows citizens to participate
in the search by uploading sightings, which are then analyzed intelligently to reduce false
reports.
3
OBJECTIVE
1. Automate Identification – Use AI-powered facial recognition and image
processing to quickly identify missing persons from CCTV footage, photos, and
social media.
2. Efficient Data Analysis – Process large amounts of data from police records,
public databases, and online sources to generate useful leads.
3. Reduce Search Time – Speed up the process of locating missing persons
compared to traditional manual methods.
4. Predictive Location Tracking – Apply machine learning algorithms to predict
possible locations of the missing person based on past movement patterns and
social connections.
5. Public Participation – Enable citizens to upload sightings or tips through AI-
enabled mobile apps and filter out false or irrelevant information.
6. Improve Accuracy & Reliability – Minimize human error by using AI models
that can continuously learn and improve detection performance.
7. Scalability – Develop a system that can be used across cities, states, or even
countries to track missing persons at a larger scale.
8. Support Families & Authorities – Provide timely updates and reliable
information to families and law enforcement to increase the chances of recovery.
4
TOOLS/PLATFORM
FindAI leverages advanced technologies in artificial intelligence, computer vision, and
data analytics to locate missing persons effectively. OpenCV is employed for image
preprocessing tasks such as face detection, cropping, and enhancement, preparing visual
input for recognition. TensorFlow or PyTorch power the deep learning models, with
architectures like YOLOv8 or FaceNet used for real-time facial recognition and person re-
identification from live CCTV or image feeds.
DeepFace library or similar frameworks enable face matching against missing person
databases with high accuracy. For communication, Twilio API or Firebase Cloud
Messaging is integrated to send real-time alerts and notifications to families or law
enforcement agencies upon identification. On the hardware side, platforms like Raspberry
Pi 4 or NVIDIA Jetson Nano allow on-edge processing of surveillance feeds in areas with
limited connectivity.
Flask or FastAPI frameworks are utilized to deploy the system as a web application or
REST API, enabling seamless integration with police databases, NGOs, and surveillance
systems. Git and GitHub are employed for version control and collaborative development,
ensuring scalability, modularity, and continuous improvement of the project.
5
HARDWARE & SOFTWARE REQUIREMENTS
HARDWRE:-
DESCRIPTION CAPACITY
MODEL HP/Dell
PROCESSOR Ryzen 3 3250U with Radeon
Graphics MEMORY (RAM) 8.00 GB
HARD DISK 512GB
KEYBOARD 115 KEY
MOUSE OPTICAL
MONITOR LED
USB NVIDIA GTX/RTX
SOFTWARE:-
1. The programming language used to develop this project is Python.
2. For deep learning frameworks, TensorFlow or PyTorch are used.
3. OpenCV and DeepFace libraries are used for image preprocessing and face
recognition.
4. Deployment is done using Flask or FastAPI for web integration.
5. MySQL / Firebase database is used for storing missing persons’ data.
6. The operating system used is Windows 11 (compatible with Linux for server
deployment).
7. For documentation and reporting, Microsoft Office (Word, Excel, PowerPoint) is
utilized.
6
DATA FLOW DIAGRAM
7
MODULES
1.Face Detection & Recognition Module
Capture Input: Collects live video feed or uploaded images from CCTV, mobile,
or web sources.
Apply AI Models: Uses YOLOv8 or FaceNet for real-time human face detection
and recognition.
Draw Bounding Boxes: Highlights detected faces with identification confidence
levels.
Database Matching: Compares detected faces with missing person records.
2.Image Preprocessing Module
Resize & Normalize: Adjusts image resolution and scales inputs for AI models.
Reduce Noise: Removes background clutter using OpenCV filters.
Enhance Quality: Improves brightness, sharpness, and clarity for accurate
recognition.
Format Conversion: Converts raw video frames into model-compatible formats.
3. Database & Matching Module
Store Records: Maintains a structured database of missing persons (photos, details,
last seen info).
Face Embedding: Uses DeepFace or feature extraction to encode facial features.
Compare Matches: Finds similarity scores between live inputs and stored records.
Update Continuously: Syncs data with law enforcement and NGO systems.
4.User Interface & Visualization Module
Live Monitoring: Displays video streams with detected/matched faces highlighted.
Show Status: Presents recognition results (Match Found / No Match) with
timestamps.
Interactive Dashboard: Provides tools for uploading missing person data and
viewing reports.
Support Decision-Making: Helps authorities track search progress and manage
alerts.
8
FUTURE SCOPE
1. Integration with National Databases – Linking with Aadhaar, passport, or police
records ensures faster and more reliable identification.
2. Crowdsourced Search via Mobile App – Citizens can upload sightings, and AI
filters false reports to help authorities.
3. Multi-modal Recognition – Expanding beyond face recognition (gait, voice,
clothing) to make the system robust in real-world conditions.
4. IoT & Smart City Integration – Using CCTV, drones, and IoT networks in
crowded areas (stations, festivals) for large-scale monitoring.
5. Real-time Predictive Analytics – AI dashboards can suggest probable locations
and movement patterns to guide search operations.
6. Blockchain for Data Security – Ensures that sensitive information about missing
persons is stored and shared securely with authorized agencies only.
7. Emergency Response Automation – Automatically alerts the nearest police
station or rescue team when a match is confirmed, reducing response delays and
saving time.
9
REFERENCES
• www.kaggle.com
• docs.python.org
• flask.palletprojects.com
• www.wikipedia.org
• https://link.springer.com/article/10.1007/s00521-023-08809-1
• https://www.mdpi.com/2571-6255/7/4/135
10
