A

Mini project Report

On

COLLEGE NOTIFICATION VOICE ALERT

Submitted in partial fulfillment of the requirements for the award of

BACHELOR OF TECHNOLOGY

In

COMPUTER SCIENCE AND ENGINEERING

By

M.SOWMYA (23TQ1A0511)

R. KAVYA (23TQ1A0526)

N. MAHESH (24TQ5A0502)

Under the Esteemed Guidance of

MRS. K. SUMA

Assistant Professor

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

SIDDHARTHA INSTITUTE OF TECHNOLOGY AND SCIENCES

(UGC - AUTONOMOUS)
(Approved by AICTE , New Delhi & Affiliated to JNTUH , Hyderabad)

Accredited by NBA and NAAC with ‘A+’ Grade

Narapally, Korremula Road, Ghatkesar, Medchal Malkajgiri(Dist)-500088

2024 – 2025

1
 SIDDHARTHA INSTITUTE OF TECHNOLOGY AND SCIENCES
(Approved by AICTE , Affiliated to JNTUH , Hyderabad v Accredited by NBA and NAAC with ‘A+’ Grade

Narapally, Korremula Road, Ghatkesar, Medchal Malkajgiri(Dist)- 500088

CERTIFICATE

This is to certify that this Project Report entitled

COLLEGE NOTIFICATION VOICE ALERT

Being Submitted

By

M.SOWMYA (23TQ1A0511)

R.KAVYA (23TQ1A0526)

N.MAHESH (24TQ5A0502)
In partial fulfillment for the award of the degree of Bachelor of Technology in Computer Science
and Engineering, Jawaharlal Nehru Technological University Hyderabad, is a record of bonafide
work carried out under my guidance and supervision. The results embodied in this project report
have not been submitted to any other University or Institute for the award of any Degree or
Diploma

Guide Head of the Department

Mrs. K Suma Mr. B Ravindar Reddy

Assistant Professor, Department of CSE HOD, Department of CSE

Internal Examiner External Examiner

2
 DECLARATION

We, M.Sowmya, R.Kavya and N.Mahesh hereby declare that the results embodied in this project
dissertation entitled “COLLEGE NOTIFICATION VOICE ALERT” is carried out by us during
the year 2024 – 2025 in partial fulfillment of the award of Bachelor of Technology in Computer
Science and Engineering from Siddhartha Institute of Technology and Sciences. It is an
authentic record carried out by us the guidance of Mrs. K Suma, Assistant Professor, Department of
Computer Science and Engineering

M.SOWMYA(23TQ1A0511)
R.KAVYA (23TQ1A0526)
N.MAHESH(24TQ5A0502)

3
 ACKNOWLEDGEMENT

Any endeavor in the field of development is a person’s intensive activity. A successful

project is a fruitful culmination of efforts by many people, some directly involved and some others
who have quietly encouraged and supported.

Salutation to be beloved and highly esteemed institute SIDDHARTHA INSTITUTE OF

TECHNOLOGY AND SCIENCES or grooming us into Computer Science and Engineering
graduate, We wish to thank our principal Dr.JANARDHAN sir for providing a great learning
environment.

We wish to express profound gratitude to B. RAVINDAR REDDY sir, Assistant Professor and
Head of the Department, Computer Science and Engineering, for his continuous encouragement to
ensure successful results in all my endeavors

We would like to thank Mrs. K SUMA mam, Assistant Professor, Department of Computer Science
and Engineering, who patiently guided and helped us throughout our project.

By
M.SOWMYA (23TQ1A0511)

R.KAVYA (23TQ1A0526)

N.MAHESH (24TQ5A0502)

4
 ABSTRACT

Now a day's Smart phones have become an irresistible part of everyone's life. With these smart
phones the human life is changed for better. In today's time the smart phone evolution has changed the
lives of every individual drastically. On touch of a button the world is coming to our fingertips. This
Mobile era has simplified our life by putting the world in our hands. The heart of these smart phones is
their Applications. There are lots of free applications available at our service. Campus Alert System is a
android notification system that enables college and administrators to send alerts from one easy-to-use
interface. Requiring android smart phone our unified alert system enables you to communicate with your
entire campus community in minutes via those communication channels most popular with students:
SMS text messaging, Email and voice notification alerts. College notification voice alerts, like those
used for announcements, emergencies, or general updates, can offer several advantages and
disadvantages. Here's a breakdown:
Keywords: Notification System, Voice Alert, Text-to-Speech (TTS), Automated Calls, Emergency
Alert, College Communication.

5
 TABLE OF CONTENTS

CHAPTER TITLE PAGE NO

ABSTRACT 5
LIST OF FIGURES 8
LIST OF ABBREVIATIONS 8
1 INTRODUCTION 9
1.1 OVERVIEW 9
2 AIM AND SCOPE 10
2.1 AIM 10
2.2 SCOPE 10
2.2.1 FUNDAMENTAL STEPS 10
IN OCR
3 LITERATURE REVIEW 11
3.1 REVIEW OF LITERATURE 11 – 16
4 METHODOLOGY 17 - 35
4.1 SYSTEM ANALSIS 17
4.1.1 EXISTING SYSTEM 17
4.1.2 PROPOSED SYSTEM 17 – 19
4.1.3 LANGUAGES USED IN THE SYSTEM 19

4.1.3.1 ABOUT PYTHON 19 – 23

LANGUAGE
4.2 SYSTEM REQUIREMENTS 23
4.2.1 HARDWARE 23
REQUIREMENTS
4.2.2 SOFTWARE REQUIREMENTS 23

4.2.2.1 CODING LANGUAGES 24 – 25

4.3 METHODOLOGY 25
4.3.1 SYSTEM ARCHITECTURE 25
4.3.2 MODULES 26
4.3.2.1 DATA PRE- 26 – 28
PROCESSING
4.3.2.2 FEATURE SELECTION 28
4.3.2.3 BUILDING AND 29
TRAINING

6
 4.3.2.4 NUMBER PLATE 29
EXTRACTION
4.3.2.5 CHARACTER 29
SEGMENTATION
4.3.2.6 OPTICAL CHARACTER 29
RECOGNITION
4.3.2.7 TEMPLATE MATCHING 29
4.3.3 UML DIAGRAMS 30
4.3.3.1 USE CASE DIAGRAM 31
4.3.3.2 SEQUENCE DIAGRAM 31
4.3.3.3 ACTIVITY DIAGRAM 32
4.4 TESTING 33
4.4.1 SOFTWARE TESTING 33
4.4.2 TEST CASE 33
4.4.3 TESTING TECHNIQUES 33 - 35
5 CONCLUSION 36
5.1 CONCLUSION 36
5.2 FUTURE WORK 36
REFERENCES 36 - 37
APPENDICES 38
SAMPLE CODE 38 - 41

7
LIST OF FIGURES

FIGURE NO. FIGURES NAME PAGE NO

4.1 System Architecture 25
4.2 Use Case Diagram 31
4.3 Sequence Diagram 32
4.4 Activity Diagram 32

LIST OF ABBREVIATIONS

OCR - Optical Character Recognition

UML - Unified Modeling Language

8
 CHAPTER 1

INTRODUCTION

In many colleges, announcements and notification are conveyed through notice boards or online
portals, which may not be accessed immediately. This project aims to implement a voice-based alert
system that audibly notifies students and faculty about events, changes, or important messages. This
enhances communication, especially for me-sensitive or emergency information.

In educational institutions, timely and effective communication plays a vital role in the smooth
functioning of daily activities. Traditional methods like notice boards, emails, or classroom
announcements often face delays or may go unnoticed by students and faculty. To overcome these
limitations, this project introduces a College Notification Voice Alert System.

This system is designed to convert text notifications into speech, enabling voice-based announcements
for important updates such as exam schedules, class cancellations, event reminders, or emergency
alerts. By integrating a text-to-speech engine, the system ensures that critical information is delivered in
real- me and is accessible to all, including visually impaired individuals. This project highlights the
practical application of voice technology to improve communication within academic environments.

1.1 Objective:
To design and develop a system that delivers college notifications via voice alerts to ensure important
messages reach students and faculty promptly and effectively.
The objective of this project is to develop a voice-based notification system for colleges that converts
text-based announcements into audible alerts. This system aims to improve the delivery of important
information to students and staff by ensuring that notifications are heard promptly and clearly,
thereby enhancing communication efficiency and accessibility within the institution.

9
 CHAPTER 2
AIM AND SCOPE

2.1 AIM
The aim of the College Notification Voice Alert System project is to develop an automated
system that delivers important college-related announcements and notifications to students and
staff using voice alerts, ensuring timely and effective communication within the campus
environment.

2.2 SCOPE
Automated Voice Announcements:
The system will convert text-based notifications (e.g., class schedules, event alerts, exam
dates, emergencies) into voice messages that can be broadcasted in real-time.

Target Users:

Students

Faculty members

Administrative staff

Delivery Platforms:

Public address (PA) system

Mobile apps (optional)

Desktop notifications with voice output

Types of Alerts Covered:

Academic alerts (class cancellations, exams)

10
Administrative messages (fee deadlines, holiday notices)

Emergency alerts (fire, weather, safety instructions)

Real-Time and Scheduled Alerts:

Notifications can be pushed instantly or scheduled for future broadcasting.

Multilingual Support (Optional Extension):

The system can be enhanced to support voice alerts in multiple languages depending on user
preferences.

Text-to-Speech Integration:
Utilizes TTS (Text-to-Speech) engines to convert notifications into natural-sounding voice
messages.

User Interface (for Admins):

Admins or college staff can input messages, select recipients, and schedule alerts via a user-
friendly interface.

11
 CHAPTER 3
LITERATURE REVIEW

3.1 REVIEW OF LITERATURE

1. Unified Alert System

Unified Alert Systems are designed to streamline communication within educational institutions,
ensuring that students, faculty, and staff receive timely and relevant notifications. These systems
integrate multiple communication channels, such as SMS, email, app notifications, and even audible-
visual alerts, to deliver messages effectively across campuses.

Key features of Unified Alert Systems include:

Multi-Channel Communication: Notifications are sent through various platforms to ensure they reach
everyone, regardless of their preferred communication method. Multi-channel communication is a
strategy that utilizes multiple platforms to deliver messages effectively, ensuring that information
reaches the intended audience promptly and reliably. This approach is particularly valuable in systems
like Unified Alert Systems, where timely dissemination of notifications is critical.

Emergency Alerts: These systems are crucial during emergencies, providing real-time updates and
instructions to ensure safety.

Integration with Existing Infrastructure: Unified systems often work seamlessly with pre-existing
technologies like PA systems, digital screens, and mobile apps.

Personalization and Targeting: Messages can be tailored to specific groups, such as students in a
particular department or faculty members in a specific building.

Accessibility: Many systems include features to assist individuals with disabilities, such as text-to-
speech and visual signaling.

12
2.AI-Driven Notification

AI-driven notifications leverage artificial intelligence to enhance communication by making it more

personalized, timely, and efficient. These systems analyze user behavior, preferences, and historical data
to deliver the right message at the right time, ensuring higher engagement and relevance.

Key Features of AI-Driven Notifications:

• Personalization: AI tailors notifications based on individual preferences, such as sending

reminders for deadlines or updates on topics of interest.

• Behavior Analysis: By studying user interactions, AI predicts the best time and channel to
send notifications, increasing the likelihood of engagement.

• Automation: Notifications are sent automatically, reducing the need for manual intervention
while maintaining accuracy and consistency.

• Real-Time Updates: AI ensures that notifications are sent instantly, keeping users informed
about critical events or changes.

• Predictive Insights: AI can identify patterns and predict user needs, such as reminding
students about upcoming exams or suggesting resources for improvement

3.Mobile Application for Academic Alert

Mobile applications for academic alerts are designed to streamline communication between
educational institutions and students, ensuring timely updates and reminders about academic activities.
These apps are particularly useful for managing schedules, tracking deadlines, and staying informed
about events.

Key Features of Academic Alert Apps:

1. Real-Time Notifications: Students receive instant alerts about class schedules, assignment
deadlines, exam dates, and campus events.
2. Customizable Alerts: Users can personalize notifications based on their preferences, such as
setting reminders for specific tasks or events.
3. Integration with Calendars: Many apps sync with popular calendar tools like Google Calendar
or Apple Calendar, allowing students to manage their academic schedules seamlessly.
4. Accessibility: These apps often include features like voice alerts and text-to-speech, making
them accessible to individuals with disabilities.

13
4.Proposed Solution

A proposed solution for a college notification voice alert system would focus on creating an efficient,
automated platform to deliver important updates, announcements, and emergency alerts using voice
technology. Here’s a structured approach:

1. System Overview:
The system would use:

• AI-driven text-to-speech conversion to transform written notifications into voice alerts.

• Cloud-based architecture for storing and distributing announcements.
• Mobile and IoT integration for alerts on smartphones and campus speakers.

2. Key Components:
• User Interface (UI): A web portal/app for administrators to record or input notifications.
• Voice Processing Engine: Converts text to speech with natural voice modulation.
• Delivery Mechanism: Push notifications, phone calls, and speaker broadcasts.
• Data Security: Encryption and authentication to protect student information.

3. Implementation Strategy:
• Develop a mobile-friendly platform compatible with Android/iOS.
• Use AI speech synthesis for clear, multilingual voice alerts.
• Integrate with existing college databases for automated updates on exams, events, and
deadlines.

14
4. Benefits and Future Enhancements:

Instant communication for students and faculty.

Accessibility improvements, especially for visually impaired individuals.

AI-based predictive alerts for personalized notifications.

Multi-language support to cater to diverse student populations.

15
 CHAPTER 4
METHODOLOGY
4.1 SYSTEM ANALYSIS
4.1.1 Existing System
There are existing projects related to college notification voice alert systems. Here are a few
examples:

• College Notification System (CNS): An Android application that allows teachers to create and
upload notices, which students can view on their dashboard. It replaces traditional notice boards
with an e-notice system.
• Automatic Android Alert Notification System: A project designed to connect an Android
application to a college’s educational web server, enabling real-time alerts for students and
instructors.
• College Notification Voice Alerts: A project focused on delivering voice-based notifications for
college announcements, improving accessibility and communication

Limitations:

Existing college notification voice alert systems have several limitations that can impact their
effectiveness. Here are some key challenges:

1. Limited Accessibility
• Some systems rely on text-based notifications, making them less effective for visually impaired
students.
• Voice alerts may not support multi-language options, restricting accessibility for diverse
student populations.

2. Delayed Notifications
• Network congestion or server downtime can cause delays in delivering alerts.
• Some systems depend on manual input, leading to slower updates for urgent announcements.

3. Lack of Integration
• Many notification systems are not integrated with college databases, requiring separate
management.
16
• Limited compatibility with IoT devices like smart speakers or campus-wide PA systems.

4. Privacy and Security Concerns

• Data breaches or unauthorized access can compromise student information.
• Some systems lack end-to-end encryption, making notifications vulnerable to interception.

5. User Engagement Issues

• Students may ignore notifications due to frequent or irrelevant alerts.
• Lack of customization options prevents users from filtering notifications based on priority.

4.1.2 Proposed System

A proposed system for a college notification voice alert aims to enhance communication
efficiency using AI-driven voice alerts. Here's a structured plan:

1. System Overview
The system would automate college notifications through voice alerts, ensuring students and faculty
receive instant updates on events, deadlines, and emergency warnings. It would be cloud-based and
integrated with mobile applications and IoT devices for better reach.

2. Key Components
• Admin Dashboard: College administrators can input notifications manually or automate event-
based alerts.
• AI Text-to-Speech Engine: Converts written notifications into natural-sounding voice alerts.
• Notification Delivery System: Uses mobile apps, phone calls, and campus speakers.
• Multi-Language Support: Ensures accessibility for diverse student populations.
• Data Security Protocols: Protects student information with encryption and user
authentication.

3. Implementation Plan

Mobile App & Web Portal: Users receive push notifications & voice alerts. Integration
with College Systems: Syncs with databases for automated event updates. IoT Devices &
Smart Speakers: Broadcast important messages across the campus. AI Predictive Alerts:
Identifies key reminders for individual students.
17
4. Benefits of the Proposed System
• Improved Accessibility: Beneficial for visually impaired students.
• Real-Time Alerts: No delay in delivering critical updates.
• Personalized Notifications: Students can filter alerts based on priority.
• Scalability: Future enhancements include AI voice assistants and chatbots for instant queries.

Advantages of OCR
A college notification voice alert system can be incredibly useful, offering several advantages:

• Instant Updates: Important announcements, like exam schedules, event reminders, and
emergency alerts, can be communicated immediately.
• Accessibility: Helps students who might miss text messages or emails by delivering information
audibly.
• Convenience: No need to constantly check a portal or inbox—alerts come straight through as
voice notifications.
• Emergency Communication: In urgent situations, voice alerts ensure that critical information
reaches students without delay.
• Reduced Miscommunication: Hearing a message directly can minimize misunderstandings
compared to text-based notifications.

It’s a smart way for colleges to keep students informed and engaged without relying solely on
traditional communication methods.

18
FEASIBILITY STUDY
A feasibility study for a college notification voice alert system will help determine whether the
project is practical and beneficial. Here's an outline of the key aspects to consider:

1. Technical Feasibility
• Availability of infrastructure (server, cloud storage, mobile app, etc.).
• Compatibility with existing college communication systems.
• Ease of integration with SMS, email, and other alert mechanisms.

2. Operational Feasibility
• How easy it is for staff and students to use the system.
• Reliability of delivering accurate and timely voice alerts.
• Training requirements for administrators and technical staff.

3. Financial Feasibility
• Costs of development, implementation, and maintenance.
• Potential funding sources (college budget, grants, sponsorships).
• Cost-effectiveness compared to traditional notification methods.

4. Legal & Ethical Considerations

• Compliance with data privacy regulations.
• Consent management for students opting in/out of alerts.
• Ethical implications of automated voice notifications.

5. Market & User Acceptance

• Expected adoption rate among students and faculty.
• Alternative solutions available in the market.
• Surveys or feedback to gauge user interest.

6. Risk Analysis
• Possible technical failures or cybersecurity threats.
• Risks of miscommunication or inaccurate alerts.
• Contingency plans in case of system downtime.

If these aspects indicate that the project is viable and beneficial, it can move forward with
development and testing.

19
TECHINICAL FEASIBILITY

1. Availability of Infrastructure

To implement a voice alert system in a college, certain infrastructure components are necessary:

• Servers: A reliable server (on-premises or cloud-based) is needed to store and manage alert data.
Cloud servers like AWS, Google Cloud, or Microsoft Azure offer scalability.
• Cloud Storage: Voice messages need to be stored for reference. Cloud storage solutions such as
Google Drive, OneDrive, or specialized databases for voice recordings can be used.
• Mobile & Web Applications: A user-friendly mobile app or web portal where students and
faculty can receive and manage alerts would enhance efficiency.
• Voice Processing Tools: AI-driven tools (such as text-to-speech systems) can automate
announcements instead of manual recordings.

2. Compatibility with Existing College Communication Systems

To ensure a seamless transition, the voice alert system must integrate with current notification tools:

• Learning Management Systems (LMS): Platforms like Moodle, Blackboard, and Google
Classroom should allow notifications to be pushed as voice alerts.
• College Websites & Portals: Voice alerts should complement existing college websites and
information portals.
• Student Database Integration: The system should access student details for personalized voice
alerts (e.g., specific reminders for exams or deadlines).

3. Ease of Integration with SMS, Email & Other Alert Mechanisms

The system should function alongside conventional messaging methods:

• SMS Alerts: APIs like Twilio or Firebase Cloud Messaging can be used to send voice-based
SMS alerts.
• Email Notifications: The system should include voice-enabled email alerts, possibly using
services like Gmail or Outlook with audio attachments.
• Push Notifications: Mobile apps should support push notifications with recorded or AI-
generated voice messages.
• IVR (Interactive Voice Response): Colleges can implement IVR for students to access
important voice-based notifications over a call.

20
 SOCIAL FEASIBILITY

The social feasibility of implementing a college notification voice alert system depends
on several human-centered and cultural factors. Here's a breakdown of how such a system
might be received in a college environment:

Social Feasibility – Factors in Favor:

1. Accessibility:
Voice alerts help students with visual impairments or reading difficulties stay
informed.
2. Urgent Communication:
Time-sensitive announcements (e.g., emergencies, last-minute class cancellations)
are more effectively delivered through voice.
3. Hands-Free Notification:
Students can receive alerts while walking, driving, or multitasking, increasing
convenience.
4. Engagement and Attention:
Voice messages may be harder to ignore than text notifications, especially in noisy
environments.

Social Feasibility – Potential Challenges:

1. Noise and Disruption:
Voice alerts might be considered disruptive in libraries, study spaces, or during
classes if not properly managed.
2. Privacy Concerns:
Students may feel uncomfortable receiving personal or academic information aloud
in public settings.
3. Cultural Sensitivities and Language Diversity:
Voice systems must support multiple languages and accents to ensure inclusivity
and avoid misunderstandings.
4. User Preference and Customization:
Some students may prefer silent modes like push notifications or emails. Lack of
opt-out options can cause dissatisfaction.

Mitigation Strategies:
• Opt-In System: Let students choose whether they want voice alerts and for what
type of notifications.
21
 • Silent Zones: Disable or modify voice alerts in sensitive areas like libraries or
during exams.
• Customizable Voice Profiles: Allow users to select voice type, language, and
delivery settings.

4.1.3 LANGUAGES USED IN THE SYSTEM

If you're developing a college notification voice alert system as a project, the
programming languages and technologies you'll use fall into several
categories: frontend, backend, voice processing (text-to-speech), and
integration. Here's a breakdown:

1. Programming Languages (Core Development)

Backend Development
• Python – Popular for integrating text-to-speech (TTS) libraries like
Google Text-to-Speech (gTTS), pyttsx3, or using APIs like Google
Cloud TTS.
• JavaScript (Node.js) – Useful for real-time notification systems and
integrating APIs.
• Java – Suitable if building an Android app or a robust server-side
application.
• C# – Useful for Windows-based applications or if using Microsoft
Azure TTS.
Frontend Development
• HTML/CSS/JavaScript – For building a web-based dashboard or
control panel.
• React / Angular / Vue.js – Modern frontend frameworks for dynamic
UI/UX.
Mobile App (if needed)
• Java/Kotlin – For Android app development.
• Swift – For iOS app development.
• Flutter (Dart) – Cross-platform mobile app.
22
 2. Voice Synthesis (TTS Libraries and APIs)
These aren't programming languages but tools/APIs you integrate using the
above languages:
• Google Text-to-Speech (Cloud API) – Works well with Python,
Node.js, etc.
• Amazon Polly (AWS) – High-quality voice synthesis with support for
many languages.
• Microsoft Azure TTS – Good voice customization options.

• pyttsx3 – Offline TTS for Python (limited voices but no internet

required).
• gTTS (Google Text-to-Speech) – Easy-to-use Python package for
online voice output.

3. Notification Handling
• Firebase Cloud Messaging (FCM) – For push notifications to
mobile/web.
• Twilio API – To send voice calls or SMS alerts.
• Email/SMS Gateways – For backup or text-based alerts.

Example Tech Stack for a College Voice Alert System:

Component Suggested Language/Tech
Backend server Python or Node.js
Voice synthesis Google TTS API (via Python/Node.js)
Web dashboard React + JavaScript
Mobile app (optional) Flutter (Dart)
Notifications (optional) FCM or Twilio

23
 4.2 SYSTEM REQUIREMENTS
4.2.1 HARDWARE REQUIREMENTS

To develop a college notifications voice alert system, you'll need both hardware and
software system requirements depending on whether it's a web app, mobile app, or
desktop system. Here's a detailed list:

1. Hardware Requirements (Development Environment)

Component Minimum Requirement Recommended
Processor (CPU) Intel i3 / AMD Ryzen 3 or better Intel i5+ / Ryzen 5+
RAM 4 GB 8 GB or more
Storage 10–20 GB free (for code, libraries) SSD, 50+ GB free
Microphone Optional (for testing voice input/output) Built-in or USB mic
Internet Required (for cloud TTS APIs, notifications) Stable broadband

4.2.2 SOFTWARE REQUIREMENTS

Operating System
• Windows 10/11, Linux (Ubuntu/Debian), or macOS
• Android Studio (if making a mobile app)
• Docker (optional, for easy deployment)

Development Tools
• Code Editor/IDE: VS Code, PyCharm, IntelliJ, Android Studio, etc.
• Web Browser: Chrome, Firefox (for testing web UI)
• API Tools: Postman or Insomnia (for testing REST APIs)

Languages and Frameworks

• Python (with gTTS, pyttsx3, Flask/Django)
• JavaScript (Node.js, React/Vue.js)
• Dart/Flutter (if targeting mobile)

3. Voice Alert Tools & APIs

24
 • Google Cloud Text-to-Speech API (API key required)
• Amazon Polly (AWS account required)
• Microsoft Azure Speech API
• Offline TTS: pyttsx3 (Python), no internet needed

4. Optional Services
• Firebase – For push notifications.
• Twilio – For SMS/voice calls.
• Database – SQLite, Firebase Firestore, MySQL, or MongoDB.
• Hosting – Heroku, Render, Vercel, or local server.

Testing & Deployment

• Emulator (for Android apps)
• Web server (e.g., Flask server or Node.js server)
• Version control: Git, GitHub or GitLab

4.2.2.1 CODING LANGUAGES

To develop a college notification voice alert system, you can use a mix of
coding languages depending on the platform (web, mobile, desktop),
functionality (voice alerts, notifications), and your tech preference.
Here's a breakdown of the key coding languages involved:

1. Backend Development Languages

(For processing logic, sending alerts, integrating APIs)
Language Key Use Cases
Easy integration with text-to-speech (e.g., gTTS, pyttsx3),
Python
ideal for fast backend development using Flask or Django
JavaScript Good for real-time applications and web APIs; integrates well
(Node.js) with Firebase
25
Language Key Use Cases
Useful for Android development and scalable backend
Java
systems
Ideal if using Microsoft Azure for voice services or building
C# (.NET)
Windows apps

2. Voice Synthesis (Text-to-Speech) Languages

(Used to convert text into audio)
Language TTS Tools Supported
Python gTTS, pyttsx3, Google Cloud TTS, Amazon Polly
JavaScript (Node.js) Google TTS, Amazon Polly via NPM packages
Java Android's built-in TextToSpeech class
C# Azure Speech SDK

3. Frontend (Web Interface) Languages

(Used for creating the user interface/dashboard)
Language Purpose
HTML/CSS Basic structure and styling of web UI
JavaScript Dynamic interaction and frontend logic
React / Angular / Vue.js Modern, responsive front-end frameworks

4. Mobile App Development Languages

(If building a mobile notification app)
Language Platform
Java / Kotlin Android native app
Swift iOS native app
Dart (Flutter) Cross-platform mobile development

26
 5. Database Query Languages
(For storing student data and notification logs)
Language Common Databases
SQL MySQL, PostgreSQL (relational databases)
NoSQL (JSON-like) Firebase, MongoDB (flexible, scalable)

Typical Tech Stack Example:

• Backend: Python with Flask + Google TTS API

• Frontend: HTML/CSS/JavaScript or React

• Database: Firebase or MySQL

• Voice Output: gTTS or Amazon Polly

• Mobile App (optional): Flutter (Dart)

4.3 METHODOLOGY
4.3.1 SYSTEM ARCHITECTURE

The system architecture for a college notification voice alert project outlines
how different components work together to send text-based notifications (like
class updates, event alerts, or emergencies) as voice messages to students
through web, mobile, or speaker systems.

1. High-Level System Architecture Overview

plaintext
CopyEdit
+--------------------------+
| Admin/Web Dashboard |
+-----------+--------------+
|
v
27
 +------------+-------------+
| Backend Server |
| (Python/Node.js/Java) |
+------------+-------------+
|
+--------------------+------------------------+
| | |
v v v
+----------+ +-----------------+ +----------------+
| Database | | TTS Service/API | | Notification API|
| (MySQL / | | (gTTS, Polly, | | (Firebase, |
| Firebase)| | Azure TTS) | | Twilio, etc.) |
+----------+ +-----------------+ +----------------+
| |
v v
+----------------------------------+ +------------------------------+
| Voice File Generation/Storage | | Send Voice/Push/SMS Alerts |
| (.mp3 or .wav) | +------------------------------+
+----------------------------------+

2. Component-wise Explanation
A. Admin/Web Dashboard (Frontend)
• Used by staff/admin to create and schedule notifications.

• Built using HTML/CSS/JavaScript or frameworks like React or Vue.js.

B. Backend Server (Logic Layer)

• Handles user requests, text processing, and API communication.

• Built using Python (Flask/Django), Node.js, or Java.

• Responsibilities:

o Accept messages from admin.

o Store data in the database.

o Call TTS API to generate voice.

28
 o Trigger alert delivery via chosen channels.
C. Database
• Stores:

o Student info (name, phone/email/device ID)

o Notification history

o Language preferences (if multilingual)

• Use MySQL, PostgreSQL, or Firebase Firestore.

D. TTS Service (Text-to-Speech API)

• Converts text to audio (voice alert)

• Options:

o gTTS (Google) – simple and free

o Amazon Polly – high-quality, many languages

o Microsoft Azure TTS

E. Notification Delivery System

• Delivers alerts to students:

o Push notifications (via Firebase Cloud Messaging)

o SMS/Voice call (via Twilio, Plivo)

o Email (via SendGrid, SMTP)

F. Audio Storage (Optional)

• Store generated audio files (.mp3, .wav)

• Use local storage, cloud storage (Google Cloud, AWS S3), or Firebase

Storage

3. Optional Add-ons
• Mobile App: Built using Flutter or Kotlin, for push alerts or playback.

• Speaker/PA Integration: Audio file streamed to physical systems (e.g.,

Raspberry Pi with speaker output).

• Multilingual Support: TTS API can choose voices based on stored

language preference.

29
 Example Workflow:
1. Admin sends: "Exam rescheduled to Monday 10 AM."
2. Backend stores message and student list in database.
3. TTS API converts text into a voice file.
4. Voice file is stored (optional).
5. Alert is sent:
o As audio push to app

o As link via SMS

o Or played directly on a PA speaker

4.3.2 MODULES

To develop a college notification voice alert system, you can divide the
project into logical modules. These modules help you structure the system into
manageable components for development, testing, and deployment.

Core Modules for the Project

Module Name Description
Handles authentication, roles (admin, staff, student),
1. User Management
and user profiles.
Admin/staff creates text messages to be sent as voice
2. Notification Input
alerts.
3. Text-to-Speech Converts notification text into voice using APIs like
(TTS) Google TTS, Amazon Polly, etc.
4. Notification Sends alerts via push notification, SMS, voice call,
Delivery email, or PA system.
5. Database Stores user data, message history, preferences, logs,
Management and voice file paths.
6. Language & Voice Allows users to select preferred language or voice
30
Module Name Description
Settings gender (if supported by TTS).
Enables scheduling alerts for future delivery (e.g.,
7. Scheduling Module
reminders, exams).
8. Audio File Handles storage, playback, and cleanup of voice files
Management (.mp3/.wav).
Web or mobile UI for admins to control and monitor
9. Dashboard Interface
notifications.
10. Logging & Tracks sent alerts, success/failure, and system usage
Reporting for analytics.

Optional or Advanced Modules

Module Name Purpose
Enables notifications in multiple languages based on
Multilingual Support
user preference.
A quick-send module for urgent alerts to all users
Emergency Broadcast
instantly.
Connects with external systems like LMS, ERP, or
Integration Module
attendance systems.
Voice Playback Streams alerts to physical speakers (e.g., for on-
System campus announcements).
Allows role-based access (e.g., only department heads
Admin Role Control
can send notices).
Notification Template Predefined message templates to speed up common
Module alerts (e.g., holiday notice).

Typical Development Roadmap by Modules

1. User Management & Dashboard UI
2. Notification Input & TTS Integration
31
 3. Delivery System (Push/SMS/Voice Call)
4. Database Setup & Audio File Handling
5. Testing, Logging, and Reporting Features

4.3.3 UML DIAGRAMS

To develop a College Notifications Voice Alert system, several UML

diagrams can help you visualize and design the system clearly. Here's a
breakdown of the most relevant UML diagrams you can use for such a
project:

1. Use Case Diagram

Purpose: Shows how users interact with the system.
Actors:
• Admin

• Faculty

• Student

• Notification System

Use Cases:
• Upload notification

• Convert text to voice

• Send alert (audio & text)

• Schedule notifications

• Manage users

2. Class Diagram
Purpose: Represents the structure of the system by showing classes and their
relationships.
Key Classes:
• User (base class)
32
 o Admin, Faculty, Student (inherited)
• Notification

o Attributes: title, message, timestamp, voiceFile

• TextToSpeechEngine

• Scheduler

• AlertDispatcher

Relationships:
• Admin/Faculty create notifications

• Notifications are processed by TTS engine

• Alerts dispatched to Students

3. Sequence Diagram
Purpose: Shows how objects interact in a specific scenario.
Scenario: Faculty uploads a notification.
Objects:
• Faculty → NotificationForm → System → TTS Engine → Notification

→ StudentDevice
Flow:
1. Faculty enters text
2. System saves notification
3. TTS engine converts text to voice
4. Alert is dispatched
5. Students receive notification (text + audio)

4. Activity Diagram
Purpose: Models the workflow of creating and sending a notification.
Activities:
• Login

• Input notification text

• Validate input

• Generate voice message

33
 • Schedule or send immediately
• Deliver notification

5. State Machine Diagram

Purpose: Tracks state transitions of a notification.
States:
• Draft → Queued → Processing (TTS) → Ready → Delivered →

Expired

6. Component Diagram (Optional but useful for deployment planning)

Purpose: Shows high-level components/modules.
Components:
• Frontend UI

• Notification Manager

• TTS Engine (e.g., Google TTS API)

• Scheduler

• Mobile App / Student Portal

4.4 TESTING

To develop a College Notifications Voice Alert system, you need to apply

several types of software testing to ensure it works correctly, is user-friendly,
and performs well under real conditions. Here's a categorized list of relevant
testing types for this project:

1. Functional Testing
Verifies that the system behaves as expected.
• Unit Testing: Test individual components like:

o Text-to-speech conversion module

o Notification creation and storage

34
 o User login and roles
• Integration Testing: Ensure components work together:
o TTS engine with the notification module

o Database integration with UI

• System Testing: Test the entire system workflow from notification

creation to student alert delivery.
• User Acceptance Testing (UAT): Final testing done with real users
(faculty/students/admin) to ensure it meets needs.

2. Non-Functional Testing
Focuses on system performance and usability.
• Performance Testing:

o Test response time for voice generation and alert delivery.

o Check load capacity when many users are logged in or receiving

notifications.
• Usability Testing:

o Is the UI intuitive for non-technical users like faculty or students?

o Are voice alerts clear and properly triggered?

• Security Testing:

o Secure login and access control.

o Protection against unauthorized notification publishing.

• Compatibility Testing:

o Check functionality on different devices (PC, Android, iOS).

o Ensure voice plays correctly across platforms.

3. Regression Testing
Run after updates to ensure new features or bug fixes haven’t broken existing
functionality.

4. Accessibility Testing
Ensures the voice alert is helpful especially for students with visual
35
impairments:
• Verify clear speech output

• Volume control or transcript availability

Example Test Cases:

Test
Description Expected Result
Case
Notification saved, converted to
TC1 Faculty submits text notification
voice
TC2 Student receives voice notification Clear playback on device
System handles 100 simultaneous
TC3 No delay or crash
alerts
TC4 Invalid login attempt Access denied
TC5 Voice alert matches text Speech output is accurate

36
 CHAPTER 5

CONCLUSION

5.1 CONCLUSION

Conclusion for College Notification Voice Alert Project

The College Notification Voice Alert system provides an innovative and
accessible way to enhance communication within educational institutions. By
combining text-based notifications with voice alerts, the system ensures that
important announcements reach all users—including those with visual
impairments or limited access to text-based platforms—promptly and clearly.
This project highlights the integration of modern technologies such as text-to-
speech (TTS) engines, real-time alert systems, and user role management to
create a reliable and user-friendly platform. It improves efficiency in
administrative communication, reduces reliance on traditional notice boards or
mass emails, and promotes inclusivity.
Through careful planning, design using UML diagrams, and comprehensive
testing (functional, non-functional, and accessibility), the system was
developed to be secure, scalable, and effective in real-world use.

Final Thought:
The project not only addresses a practical problem in colleges but also
provides valuable experience in system design, software development, and
real-world deployment practices.

37
 APPENDICES

A) SAMPLE CODE

Here’s a long and simple code for a College Notification Voice Alert project
using HTML, CSS, and JavaScript. This project allows you to:
• Select a role (Admin or Faculty)
• Type a notification message
• Hear the voice alert (via the browser’s built-in speech synthesis)
• View a history of past notifications (stored in memory)

Project Files Structure

pgsql
CopyEdit
college-notification/
├── index.html
├── style.css
└── script.js

index.html – HTML (Structure)

html
CopyEdit
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>College Notification Voice Alert</title>
<link rel="stylesheet" href="style.css">
</head>
<body>

<div class="container">
<h1>College Notification Voice Alert System</h1>
38
 <!-- Form to input notification -->
<div class="form">
<label for="role">Select Role:</label>
<select id="role">
<option value="">-- Select Role --</option>
<option value="Admin">Admin</option>
<option value="Faculty">Faculty</option>
</select>

<label for="message">Enter Notification Message:</label>

<textarea id="message" rows="4" placeholder="Type your notification
message here..."></textarea>

<button onclick="sendNotification()">Send Notification</button>

</div>

<!-- Notification history -->

<div class="history">
<h2>Notification History</h2>
<div id="historyBox" class="history-box">
<p>No notifications yet.</p>
</div>
</div>
</div>

<script src="script.js"></script>
</body>
</html>

style.css – CSS (Styling)

css
CopyEdit
/* Reset some default styles */
*{
39
 margin: 0;
padding: 0;
box-sizing: border-box;
}

body {
font-family: Arial, sans-serif;
background-color: #f4f7fc;
padding: 40px;
}

.container {
max-width: 700px;
background-color: #ffffff;
margin: auto;
padding: 30px;
border-radius: 10px;
box-shadow: 0 0 20px rgba(0, 0, 0, 0.1);
}

h1 {
text-align: center;
color: #2f3d4e;
margin-bottom: 20px;
}

.form label {
display: block;
margin-top: 15px;
font-weight: bold;
color: #333;
}

.form select,
.form textarea {
width: 100%;
40
 padding: 10px;
margin-top: 5px;
font-size: 14px;
border-radius: 5px;
border: 1px solid #ccc;
}

.form textarea {
resize: none;
}

button {
display: block;
width: 100%;
padding: 12px;
background-color: #3498db;
color: white;
border: none;
border-radius: 5px;
font-size: 16px;
cursor: pointer;
margin-top: 20px;
transition: background-color 0.3s;
}

button:hover {
background-color: #2980b9;
}

.history {
margin-top: 40px;
}

.history h2 {
color: #2f3d4e;
margin-bottom: 10px;
41
}

.history-box {
max-height: 200px;
overflow-y: auto;
background-color: #f7f7f7;
padding: 15px;
border-radius: 5px;
border: 1px solid #ddd;
}

.history-box p {
font-size: 14px;
color: #333;
margin-bottom: 10px;
}

script.js – JavaScript (Logic and Voice Alert)

javascript
CopyEdit
// Function to handle sending notification and voice alert
function sendNotification() {
const role = document.getElementById("role").value;
const message = document.getElementById("message").value.trim();

if (!role || !message) {
alert("Please select a role and enter a message.");
return;
}

// Get the current timestamp

const timestamp = new Date().toLocaleString();

// Build the notification message to display and read out loud

const fullMessage = `[${timestamp}] ${role}: ${message}`;
42
 // Display the message in the notification history
const historyBox = document.getElementById("historyBox");
const newNotification = document.createElement("p");
newNotification.textContent = fullMessage;
historyBox.appendChild(newNotification);

// Clear the message input

document.getElementById("message").value = "";

// Speak the notification message using SpeechSynthesis API

const utterance = new SpeechSynthesisUtterance(message);
window.speechSynthesis.speak(utterance);
}

How It Works:
1. HTML provides the basic structure for the notification system. You can
select a role (Admin or Faculty) and input a message.
2. CSS styles the application, making it look clean and modern.
3. JavaScript handles the logic:
o When you click "Send Notification", the script:
▪ Reads the role and message.
▪ Displays the notification message in the "Notification
History" box.
▪ Clears the input field for the next message.
▪ Uses the SpeechSynthesisUtterance API to speak the
message aloud.

How to Use:
1. Enter the Role (Admin or Faculty).
2. Type a Message in the text area.
3. Click "Send Notification".
o The message will be spoken aloud by the browser.
o The message will appear in the "Notification History" section, with
a timestamp.
43
4. You can add more notifications, and they will appear in the history
section.

What You Can Improve or Add Later:

• Persistent Storage: Store notifications in the browser’s local storage so
that they persist after the page reloads.
• Input Validation: Add more input validation (e.g., ensure a message is
not empty).
• Database Integration: Use a backend service to save the messages in a
database for real-time access.

44
45
4.1 METHODOLOGY
4.1.1 SYSTEM ARCHITECTURE

Fig 4.1 System Architecture

46
 The projected system is to observe every character from range plate one by one.
This could be done by morphological operation. It includes a way to section all the
characters employed in the quantity plate. Range plate extraction is that stage
wherever vehicle range plate is detected. The detected range plate is pre-processed
to get rid of the noise then the results passed to the section half to segment the one
by one character from the extracted range plate. The divided characters normalized
associate degreed passed to an OCR formula. Ultimately the optical character info
is going to be regenerate into encoded text. The characters recognized exploitation
template matching. The ultimate output should be within the type of string of
characters.

4.1.2 MODULES
4.1.2.1 Data Pre-Processing

The entries are present in the dataset. The null values are removed using df =
df.dropna() where df is the data frame. The categorical attributes
(Date,High,Low,Close,Adj value) are converted into numeric using Label Encoder.
The date attribute is splitted into new attributes like total which can be used as
feature for the model.

1. DataCleaning:

The data can have many irrelevant and missing parts. To handle this part, data
cleaning is done. It involves handling of missing data, noisy data etc.

2. DataTransformation:

This step is taken in order to transform the data in appropriate forms suitable for
mining process.

3. DataReduction:

Since data mining is a technique that is used to handle huge amount of data.While
working with huge volume of data, analysis became harder in such cases.In order
to get rid of this, we uses data reduction technique. It aims to increase the storage
efficiency and reduce data storage and analysis costs.

47
Convert color to grayscale

Three algorithms for converting color to grayscale

The lightness method averages the most prominent and least prominent
colors: (max(R, G, B) + min(R, G, B)) / 2. The average method simply averages
the values: (R + G + B) / 3. The luminosity method is a more sophisticated version
of the average method

Gaussian filter

A Gaussian filter is a linear filter. It's usually used to blur the image or to reduce
noise. The Gaussian filter alone will blur edges and reduce contrast. The Median
filter is a non-linear filter that is most commonly used as a simple way to reduce
noise in an image.

Edge Detection

Each image (video frame) has three significant features to achieve detection goals.
These features include: edges, contours and points. Among mentioned features, an
appropriate option is to use edge pixels. Processing of image pixels enables us to
find edge pixels, which are the main features of passing vehicles in a roadway
video frame. Edge detection process is demonstrated in a binary image (threshold)
with the detected edge pixels. The next step is to extract moving edges from
sequential video frames and process the resulting edge information to obtain
quantitative geometric measurements of passing vehicles.

Contour

Contour map uses contours or color-coded regions helps us to visualize 3D data in

two dimensions. Contour maps are also used to visualize the error surfaces in deep
learning/machine learning optimization techniques.

Masking

The idea behind masking is to have two additional arrays that record whether an
input or output is actually present for a given time step and example, or whether
the input/output is just padding.

Model Creation :
48
CNN Algorithm

A convolutional neural network (CNN) is a specific type of artificial neural

network that uses perceptrons, a machine learning unit algorithm, for supervised
learning, to analyze data. CNNs apply to image processing, natural language
processing and other kinds of cognitive tasks. CNN image classifications takes an
input image, process it and classify it under certain categories.

We have 4 steps for convolution:

➢ Line up the feature and the image

➢ Multiply each image pixel by corresponding feature pixel

➢ Add the values and find the sum

➢ Divide the sum by the total number of pixels in the feature

Training

The training data set in Machine Learning is the actual dataset used to train the
model for performing various actions. This is the actual data the ongoing
development process models learn with various API and algorithm to train the
machine to work automatically.

Testing

It uses patterns identified by your machine learning algorithms to predict. the

machine recognizes patterns in the data, the cross-validation data is used to ensure
better accuracy and efficiency of the algorithm used to train the machine, and the
test data is used to see how well the machine can predict based on its training.

4.1.2.2 Feature selection:

Features selection is done which can be used to build the model. The attributes
used for feature selection are Date,Price,Adj close, Forecast X coordinate , Y
coordinate, Latitude , Longitude, Hour and month.

49
 4.1.2.3 Building and Training Model:

After feature selection location and month attribute are used for training. The
dataset is divided into pair of xtrain ,ytrain and xtest, y test. The algorithms model
is imported form skleran. Building model is done using model. Fit (xtrain, ytrain).
This phase would involve supervised classification methods like linear regression,
Ensemble classifiers (like Adaboost, Random Forest Classifiers), etc.

4.1.2.4 Number Plate Extraction

The captured image is in capital RGB format. It is converted into grayscale image
and into binary image.

4.1.2.5 Character Segmentation

The character segmentation part further segments the character individually from
the extracted number plate. From input image the first process will be to crop out
the number plate characters from starting to the ending point leaving all the extra
wide spaces from top to below and from right to left as it is. Characters are equally
fit in the plate region. For easy comparison of the input character with the character
in the data base the result is normalized into the character set as the size of the
images in the database.

4.1.2.6 Optical Character Recognition

The optical character recognition is a recognition method in which the input is an

image and the output is string of character. OCR is a process which separates the
different characters from each other taken from an image. Template matching is
one of the approaches of OCR. The cropped image is compared with the template
data stored in database. OCR automatically identifies and recognizes the characters
without any indirect input. The characters on the number plate have uniform fonts
then the OCR for number plate recognition is less complex as compared to other
methods.

4.1.2.7 Template Matching

Template matching affects the accuracy of Automatic number plate recognition

50
 4.1.3 UML DIAGRAMS

UML is simply another graphical representation of a common semantic

model.UML provides a comprehensive notation for the full life cycle of object
oriented development. Unified Modeling Language is a general purpose
developmental, modeling language in the field of software engineering that is
intended to provide a standard way to visualize the design of the system. UML is a
standard language for specifying, visualizing, and documenting of software
systems and created by Object Management Group (OMG) in 1997.There are three
important type of UML modeling are Structural model, Behavioral model, and
Architecture model. To model a system the most important aspect is to capture the
dynamic behavior which has some internal or external factors for making the
interaction. These internal or external agents are known as actors. It consists of
actors, use cases and their relationships. In this fig we represent the Use Case
diagram for our project.

The Unified Modeling Language is a standard language for specifying,

Visualization, Constructing and documenting the artifacts of software system, as
well as for business modeling and other non-software systems.

The UML represents a collection of best engineering practices that have proven
successful in the modeling of large and complex systems.

The UML is a very important part of developing objects oriented software and the
software development process. The UML uses mostly graphical notations to
express the design of software projects.

GOALS:

The Primary goals in the design of the UML are as follows:

1. Provide users a ready-to-use, expressive visual modeling Language so that they

can develop and exchange meaningful models.

2. Provide extendibility and specialization mechanisms to extend the core

concepts.

3. Be independent of particular programming languages and development process.

51
4. Provide a formal basis for understanding the modeling language.

5. Encourage the growth of OO tools market.

6. Support higher level development concepts such as collaborations, frameworks,

patterns and components.

4.1.3.1 USECASE DIAGRAM

A use case is a set of scenarios that describing an interaction between a user and a
system. A use case diagram displays the relationship among actors and use cases.
The two main components a user or another system that will interact with the
system modeled. A use case is an external view of the system that represents some
action the user might perform in order to complete a task.

Fig 4.2 Use case diagram

4.1.3.2 SEQUENCE DIAGRAM

A sequence diagram in Unified Modeling Language (UML) is a kind of

interaction diagram that shows how processes operate with one another and in
what order. It is a construct of a Message Sequence Chart. Sequence diagrams are
sometimes called event diagrams, event scenarios, and timing diagrams.

52
 Fig 4.3 Sequence diagram

4.1.3.3 Activity Diagram

Activity diagrams are graphical representations of workflows of stepwise activities
and actions with support for choice, iteration and concurrency. In the Unified
Modeling Language, activity diagrams can be used to describe the business and
operational step-by-step workflows of components in a system. An activity
diagram shows the overall flow of control.

Fig 4.4 Activity diagram

53
4.2 TESTING
4.2.1 Software Testing
General In a generalized way, we can say that the system testing is a type of
testing in which the main aim is to make sure that system performs efficiently and
seamlessly. The process of testing is applied to a program with the main aim to
discover an unprecedented error, an error which otherwise could have damaged the
future of the software. Test cases which brings up a high possibility of discovering
and error is considered successful. This successful test helps to answer the still
unknown errors.

4.2.2 TEST CASE

Testing, as already explained earlier, is the process of discovering all possible
weak-points in the finalized software product. Testing helps to counter the working
of sub-assemblies, components, assembly and the complete result. The software is
taken through different exercises with the main aim of making sure that software
meets the business requirement and user-expectations and doesn’t fails abruptly.
Several types of tests are used today. Each test type addresses a specific testing
requirement.

4.2.3 Testing Techniques

A test plan is a document which describes approach, its scope, its resources and
the schedule of aimed testing exercises. It helps to identify almost other test item,
the features which are to be tested, its tasks, how will everyone do each task, how
much the tester is independent, the environment in which the test is taking place,
its technique of design plus the both the end criteria which is used, also rational of
choice of theirs, and whatever kind of risk which requires emergency planning. It
can be also referred to as the record of the process of test planning. Test plans are
usually prepared with signification input from test engineers.

(I) UNIT TESTING

In unit testing, the design of the test cases is involved that helps in the
validation of the internal program logic. The validation of all the decision
branches and internal code takes place. After the individual unit is

54
 completed it takes place. Plus it is taken into account after the individual
united is completed before integration. The unit test thus performs the basic
level test at its component stage and test the particular business process,
system configurations etc. The unit test ensures that the particular unique
path of the process gets performed precisely to the documented
specifications and contains clearly defined inputs with the results which are
expected.

(II) INTEGRATION TESTING

These tests are designed to test the integrated software items to determine
whether if they really execute as a single program or application. The testing
is event driven and thus is concerned with the basic outcome of field. The
Integration tests demonstrate that the components were individually
satisfaction, as already represented by successful unit testing, the
components are apt and fine. This type of testing is specially aimed to
expose the issues that come-up by the components combination.

(III) FUNCTIONAL TESTING

The functional tests help in providing the systematic representation that

functions tested are available and specified by technical requirement,
documentation of the system and the user manual.

(IV) SYSTEM TESTING

System testing, as the name suggests, is the type of testing in which ensure
that the software system meet the business requirements and aim. Testing of
the configuration is taken place here to ensure predictable result and thus
analysis of it.System testing is relied on the description of process and its
flow, stressing on pre driven process and the points of integration.

55
(V) WHITE BOX TESTING

The white box testing is the type of testing in which the internal
components of the system software is open and can be processed by the
tester. It is therefore a complex type of testing process. All the data
structure, components etc. are tested 26 by the tester himself to find out a
possible bug or error. It is used in situation in which the black box is
incapable of finding out a bug. It is a complex type of testing which takes
more time to get applied.

(VI) BLACK BOX TESTING

The black box testing is the type of testing in which the internal
components of the software is hidden and only the input and output of the
system is the key for the tester to find out a bug. It is therefore a simple type
of testing. A programmer with basic knowledge can also process this type of
testing. It is less time consuming as compared to the white box testing. It is
very successful for software which are less complex are straight-forward in
nature. It is also less costly than white box testing.

(VII) ACCEPTANCE TESTING

User Acceptance Testing is a critical phase of any project and requires

significant participation by the end user. It also ensures that the system
meets the functional requirements.

56
 CHAPTER 5

CONCLUSION

5.1 CONCLUSION

In this work, we have presented technique to recognize number plate of

vehicles. For this, we introduced Image capture, preprocessing, edge
detection, segmentation, character resizing, feature extraction and finally
recognized character of number plate using machine learning algorithms.
Dataset creation consisted number of images which are collected real times,
parking and etc.

5.2 FUTURE WORK

Future work lies in producing more accurate results with lesser response
time according to the prescribed specifications of vehicle number plates and
automated system software is to be developed in future work.

REFERENCES

1.A New Approach for Vehicle Number Plate Detection, Sarthak Babbar ;
Saommya Kesarwani ; Navroz Dewan ; Kartik Shangle ; Sanjeev Patel,
2018 Eleventh International Conference on Contemporary Computing (IC3)

2. A hierarchical license plate recognition system using supervised K-means

and Support Vector Machine, Wei-Chen Liu ; Cheng-Hung Lin, 2017
International Conference on Applied System Innovation (ICASI)

3. Deep Learning System for Automatic License Plate Detection and

Recognition, Zied Selmi ; Mohamed Ben Halima ; Adel M. Alimi, 2017

57
14th IAPR International Conference on Document Analysis and
Recognition (ICDAR)

4. Automatic number plate recognition for motorcyclists riding without

helmet, Yogiraj Kulkarni ; Amit Kamthe ; Shubhangi Bodkhe ; Archana
Patil, 2018 International Conference on Current Trends towards Converging
Technologies.

5. Automatic car number plate recognition, Anumol Sasi ; Swapnil Sharma ;

Alice N. Cheeran, 2017 International Conference on Innovations in
Information, Embedded and Communication Systems (ICIIECS)

6. License Plate Detection with Machine Learning Without Using Number

Recognition, Kazuo Ohzeki ; Max Geigis ; Stefan Alexander Schneider,
2019 Federated Conference on Computer Science and Information Systems
(FedCSIS)

7. A New Convolutional Architecture for Vietnamese Car Plate

Recognition, Thanh-Nga Nguyen ; Duc-Dung Nguyen, 2018 10th
International Conference on Knowledge and Systems Engineering (KSE)

8. Bangladeshi License Plate Recognition Using Adaboost Classifier,

Prashengit Dhar ; Md. Zainal Abedin ; Razuan Karim ; Fatema-Tuj-Johora ;
Mohammad Shahadat Hossain, 2019 Joint 8th International Conference on
Informatics, Electronics & Vision (ICIEV) and 2019 3rd International
Conference on Imaging, Vision & Pattern Recognition (icIVPR)

9. Long distance Automatic Number Plate Recognition under perspective

distortion using zonal density and Support Vector Machine, Noprianto ;
Sunu Wibirama ; Hanung Adi Nugroho, 2017 3rd International Conference
on Science and Technology - Computer (ICST)

10. Extraction of number plate images based on image category

classification using deep learning, Yoshihiro Shima, 2016 IEEE
International Symposium on Robotics and Intelligent Sensors (IRIS)
58
 APPENDICES

A) SAMPLE CODE

from flask import Flask,url_for,request,render_template,redirect,session

import sqlite3
from werkzeug.utils import secure_filename
import os
import pytesseract
from PIL import ImageFilter
from PIL import Image
import datetime
app=Flask( name )
app.config['UPLOAD_FOLDER'] = './media'
app.secret_key="Rudy"
vnumlist=[]
parkingslot=[]
slotname=None
slotnamelist=[]
pytesseract.pytesseract.tesseract_cmd=r"C:\Program
Files\Tesseract-OCR\tesseract.exe"
@app.route('/',methods=["GET","POST"])
def login():
username=None
password=None
err="Invalid username and password"
if request.method=='POST':
session['username']=request.form['uname']
session['vid']=request.form['pwd']
username=request.form['uname']
password=request.form['pwd']
conn = sqlite3.connect("carparking.db")
r=conn.cursor()

59
 r.execute("select name,pwd from userregister where name=? and
pwd=?",(username,password))
rows=r.fetchall()
if username=='Admin' and password=='Admin':
return redirect(url_for('Admin'))
else:
if len(rows)!=0:
for i in rows:
if i[0]==username and i[1]==password:
return redirect(url_for('userpage'))
#return render_template('user.html',username=username)
else:
return render_template('login.html',err=err)
else:
return render_template('login.html',err=err)
return render_template('login.html')
@app.route('/reg',methods=["GET","POST"])
def reg():
uname=None
pwd=None
phn=None
ema=None
vtype=None
vnum=None
msg="Register successfully"
if request.method=='POST':
uname=request.form['txt']
pwd=request.form['passw']
phn=request.form['phn']
ema=request.form['ema']
vtype=request.form['vtype']
vnum=request.form['vnum']
try:
import sqlite3
table_name = 'userregister'
60
 conn = sqlite3.connect("carparking.db")
c = conn.cursor()
c.execute('create table if not exists ' + table_name + ' (name
varchar(50),pwd varchar(50) primary key,phn varchar(50),ema
varchar(50),vtype varchar(50),vnum varchar(50))')
c.execute('insert into '+table_name+' values
(?,?,?,?,?,?)',(uname,pwd,phn,ema,vtype,vnum))
conn.commit()
conn.close()
flash("Register successfully")
except:
return render_template('registration.html',msg=msg)
# return render_template('registration.html')
else:
return render_template('registration.html')
return render_template("registration.html")
@app.route('/userpage',methods=["POST","GET"])
def userpage():
err="Your not authorized to park here."
sloterr="Parking slot was full"
if request.method=='POST':
image = request.files['ocrImage']
text = ''
filename = secure_filename(image.filename)
image.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
img = Image.open(os.path.join(app.config['UPLOAD_FOLDER'],
filename))
text = pytesseract.image_to_string(img)
print(text)
session["vnumm"]=text.strip()
conn=sqlite3.connect("carparking.db")
r=conn.cursor()
r.execute("select name,phn,vtype,vnum from userregister where
vnum=?",(session["vnumm"],))
rows=r.fetchall()
61
li=[]
if len(rows)!=0:
if rows[0][3]==session["vnumm"]:
ss=conn.cursor()
ss.execute("select slot from parkingslot where status=?",("available",))
slotrow=ss.fetchall()
if len(slotrow)!=0:
for i in slotrow:
li.append(i)
session["slot"]=li[0]
return
render_template("user.html",rows=rows,slotrow=session["slot"])
else:
return render_template("user.html",rows=rows,err=sloterr)
else:
print("noo")
else:
return render_template("user.html",err=err)
return render_template('user.html',text=session["vnumm"])
else:
return render_template("user.html")
return render_template('user.html')
if name ==' main ':
app.run(debug=True)

62