SAGE SCHOOL OF COMPUTER APPLICATION

DEPARTMENT OF COMPUTER APPLICATION

PBL PRESENTATION ON

AIFINDHUB : SMART LOST AND FOUND SOLUTION

Under the Supervision of : PRESENTED BY :

Mrs. Smriti Jain CHHAVI GAJNANI (22BCA3CCM10014)
Asst. Prof., School of CA, KRISHIKA JAISWAL (22BCA3CCM10022)
SSOCA
OUTLINE

• Introduction
• Literature Survey
• Objectives and Scope
• Proposed work
• Methodology
• Requirements
• Technology used
• Project timeline
• Conclusion
INTRODUCTION

• In today's fast-paced world, misplacing items like keys, wallets, or smartphones is a common occurrence,
often resulting in time-consuming searches and inconvenience.

• This AI-Based Lost and Found System is an innovative solution designed to alleviate the frustration of losing
personal belongings and enhance the efficiency of their recovery.

• By combining AI-driven image recognition with crowdsourcing, our system streamlines the process of
identifying and retrieving lost items, fostering a sense of community engagement.

• Users can register their belongings, and when these items are found and reported by others, our AI system
swiftly matches and notifies the owners, facilitating quick and accurate recovery.
LITERATURE SURVEY

• Tile
Tile is an American consumer electronics company which produces tracking devices that users can
attach to their belongings such as keys and backpacks. "Tiles", that can be attached to items such as
keychains. By attaching the device, a user can later use the Tile app to help locate the item if it is lost.
The first devices were delivered in 2013. allows users to track the devices using Bluetooth 4.0 in
order to locate lost items or to view their last detected location.[1]
• TrackR
Trackr was produced by the company Phone Halo and was inspired by the founders' losing their keys
on a beach during a surfing trip. The founders of Phone Halo began working on TrackR in 2009. It a
commercial key finder that assisted in the tracking of lost belongings and devices. TrackR rebranded
itself to Adero, TrackR shut down its services and removed its apps in August 2021.[2]
OBJECTIVES

• To develop an AI-powered system that significantly improves the efficiency and accuracy of lost
item recovery for users.
• To implement advanced image recognition algorithms to identify lost items in user-submitted
images, making the matching process more precise and efficient.
• To seamlessly integrate cutting-edge AI and machine learning techniques to improve the accuracy
and speed of item identification.
• To contribute to reducing the overall loss rate by encouraging users to return found items through
the platform.
• To create an intuitive and user-friendly web app interface that simplifies the item registration
process and enhances the user experience.
SCOPE

• Travelers can use the app to find lost items during their trips, such as passports, tickets, or cameras,
helping them avoid disruptions in their journeys.
• Educational institutions and workplaces can adopt the app to assist students or employees in
finding lost items within their premises, enhancing organizational efficiency.
• In public transportation systems to assist passengers in finding lost items and improving the
overall travel experience.
• Restaurants and eateries can offer the app to patrons who may leave behind personal belongings,
like wallets or smartphones.
• Hotels and lodging facilities can adopt the app to help guests locate misplaced items in their rooms
or common areas.
PROPOSED WORK

• To collect lost item pictures and descriptions.

• To teach the computer to recognize items from pictures.
• To teach the computer to understand written descriptions.
• To combine image recognition and description understanding.
• To create an website.
• To test the system with different items.
USE-CASE DIAGRAM
ENTITY RELATIONSHIP DIAGRAM
METHODOLOGY

• Gather a diverse database of item images and descriptions from users.

• Train an AI model to recognize lost items from these images.
• Develop an algorithm to match lost items with found item photos.
• Encourage users to verify potential matches to improve accuracy.
• Establish a feedback system for user input and system improvement.
METHODOLOGY(FLOW DIAGRAM)
REQUIREMENTS

• HARDWARE REQUIREMENTS 
• CPU : A multicore processor for training machine learning models efficiently.
• GPU : A powerful GPU is highly required for training deep learning models quickly.
• RAM : A minimum of 8 GB of RAM is required for machine learning tasks
• Storage : SSD storage for faster data access and model loading.
• Internet Connection : A stable internet connection for data collection, updates, and potential
cloud-based services.
• Camera : Our project involves using a camera for image capture.
REQUIREMENTS

• SOFTWARE REQUIREMENTS 
• Operating System : Linux or Windows.
• Programming Languages : Python
• Development Environment : Integrated Development Environment (IDE) such as PyCharm, or Visual
Studio Code for coding and testing.
• Machine Learning Libraries : TensorFlow or PyTorch for building and training machine learning
models. Scikit-learn for data preprocessing and evaluation.
• Deep Learning Framework : like Keras or Fastai.
• Database Management : A relational database management system (RDBMS) like PostgreSQL or
MySQL for storing data.
• Web Development Tools : like HTML, CSS, JavaScript, and a framework like Django or Flask for
backend development.
UI/UX DESIGN
UI/UX DESIGN
UI/UX DESIGN
TECHNOLOGY USED

• Artificial Intelligence (AI) & Machine Learning (ML)

• Convolutional Neural Networks(CNN)
• Natural Language Processing (NLP)
• Image Recognition
• Database Management
• Web Development
• UI/UX Design
 CHHAVI KRISHIKA

September October November

Week 01 Week 02 Week 03 Week 04 Week 01 Week 02 Week 03 Week 04 Week 01 Week 02 Week 03 Week 04

Project Planning
and Research
Learning and
Skill Acquisition
Data Collection
and Preparation
AI Model
Development
Database
Development
Web Development

Final Testing
Documentation
CONCLUSION

• In conclusion, the implementation of an AIML-powered Lost and Found solution website

represents a significant leap forward in improving the efficiency and effectiveness of lost
item recovery. By leveraging artificial intelligence and natural language processing, this
platform simplifies the reporting of lost items and accelerates the process of matching
them with found items. Its user-friendly interface and AI-driven chatbot make it
accessible to a wide range of users, enhancing the overall experience. With scalability,
enhanced matching capabilities, and a commitment to data security, this solution holds
great promise in facilitating successful reunions and serving as a valuable asset to
communities and organizations alike.
REFERENCES

• [1] https://en.wikipedia.org/wiki/Tile
• [2] https://en.wikipedia.org/wiki/TrackR
THANK YOU