BS Computer Science Dissertation Project Report Template

Download PDF

/ 39

100%

Document text

[Title of the Project]

RIPHAH

INTERNATIONAL

UNIVERSITY

By:

Full Name – Team Member 1

CMS Number

Full Name – Team Member 2

CMS Number

Full Name – Team Member 3

CMS Number

Supervised by:

[Full Name of Supervisor]

Faculty of Computing

Riphah International University, Islamabad

Spring/Fall 20xx

A Dissertation Submitted To

Faculty of Computing,

Riphah International University, Islamabad

As a Partial Fulfillment of the Requirement for the Award of the

Degree of

Bachelors of Science in Computer Science

Faculty of Computing

Riphah International University, Islamabad

Date: [date of final presentation]

Final Approval

This is to certify that we have read the report submitted by name of student(s) (CMS #), for the partial fulfillment of the requirements for the degree of the Bachelors of Science in Computer Science (BSSE). It is our judgment that this report is of sufficient standard to warrant its acceptance by Riphah International University, Islamabad for the degree of Bachelors of Science in Computer Science (BSSE).

Committee:

1 __________________________

[Name Supervisor]

(Supervisor)

2 __________________________

[Name of HOD/chairman]

(Head of Department/chairman)

Declaration

We hereby declare that this document “[Project Title]” neither as a whole nor as a part has

been copied out from any source. It is further declared that we have done this project with the

accompanied report entirely on the basis of our personal efforts, under the proficient guidance

of our teachers, especially our supervisor [insert name of Supervisor(s)]. If any part of the

system is proved to be copied out from any source or found to be reproduction of any project

from anywhere else, we shall stand by the consequences.

____________________

[Name of Student 1]

[CMS #]

____________________

[Name of Student 2]

[CMS #]

____________________

[Name of Student 3]

[CMS #]

Dedication

Insert dedication here…

Acknowledgement

First of all we are obliged to Allah Almighty the Merciful, the Beneficent and the source of all Knowledge, for granting us the courage and knowledge to complete this Project.

[Students will acknowledge here anyone who has helped in the project. It can include

Supervisor(s), Teachers, Classmates, Friends and Family]

________________________

[Name of Student 1]

[CMS #]

________________________

[Name of Student 2]

[CMS #]

________________________

[Name of Student 3]

[CMS #]

Abstract

Text in 12-Point Size, Times New Roman, 1.5 Line Spacing.

Table of Contents i

Table of Contents

Table of Contents................................................................................................................ i

List of Tables................................................................................................................... iii

List of Figures................................................................................................................ iv

Abstract............................................................................................................................... 1

1.1 Introduction........................................................................................................................... 3

1.2 Goals and Objectives..........................................................................................................3

1.3 Scope of the Project.........................................................................................................4

1.4 Summary.......................................................................................................................4

Literature Review....................................................................................................................6

2.1 Introduction......................................................................................................................6

2.2 Background and Problem Elaboration.................................................................................6

2.3 Detailed Literature Review...............................................................................................7

2.3.1 Definitions.................................................................................................................7

2.3.2 Related Research Work 1............................................................................................8

2.3.3 Related Research Work 2............................................................................................9

2.4 Literature Review Summary Table...................................................................................10

2.5 Research Gap..................................................................................................................11

2.6 Problem Statement..........................................................................................................12

3.1 Requirements..................................................................................................................15

3.1.1 Requirement Elicitation Techniques:....................................................................15

3.2 Functional Requirements.................................................................................................16

3.2.1 Functional Requirements.........................................................................................16

3.2.2 Non-Functional Requirements................................................................................16

3.2.3 Hardware and Software Requirements.................................................................16

3.3 Proposed Methodology..................................................................................................17

3.3.1 Data Collection........................................................................................................17

3.3.2 Preprocessing..........................................................................................................17

3.3.3 Model Selection.........................................................................................................17

3.3.4 Model Training.........................................................................................................18

3.3.5 Integration of Freshness Detection.................................................................18

3.3.6 Deployment and Integration.................................................................................18

System Architecture............................................................................................................19

Use Cases............................................................................................................................19

1.1.1 Sample Use Case Name Here............................................................................19

Database Design..................................................................................................................20

Sequence diagram............................................................................................................21

CNN Architecture diagram............................................................................................25

Implementation and Test Cases....................................................................................26

Implementation....................................................................................................................26

1.1.2 Implementation of First Component/Algorithm................................................26

Test case Design and description..................................................................................26

1.1.3 Sample Test case No.1.....................................................................................26

1.1.4 Sample Test case No.2.....................................................................................26

Test Metrics.................................................................................................................27

1.1.5 Sample Test case Metric.No.1....................................................................27

1.1.6 Sample Test case Metric.No.2....................................................................27

1.1.7 Sample Test case Metric.No.3....................................................................27

Experimental Results and Analysis................................................................................28

Conclusion and Future Directions..................................................................................29

References.......................................................... 30

Appendix................................................................. 31

Appendix A: Guidelines................................................... 31

Appendix B: Heading of Sample Appendix B................................. 31

Formatting Guidelines......................................................... 32

Heading 1....................................................................... 32

Heading 2....................................................................... 32

1.1.8 Heading 3................................................................. 32

List of Tables iii

List of Tables

Table 1...........................................................................................................................11

Table 2...........................................................................................................................12

Table 3: This is Sample table caption.................................................................25

Table 4: This is Sample table caption.................................................................25

List of Figures iv

List of Figures

Figure 1: List of Styles..........................................................1

Figure 2: IEEE Reference style....................................................1

Abstract

An Abstract is a short summary of the work being reported. It should state: the purpose, findings, and conclusion of your work without commenting on or evaluating the work itself. It should be only one paragraph at least half a page long.

Your Project Title Here

Chapter 1:

Introductio[unreadable]

1.1 Introduction

Our project aims to revolutionize fruit classification, shelf-life detection, and quality grading through advanced technology. We're leveraging artificial intelligence and computer vision to address key challenges in agriculture and food industries. Our objectives include developing a system for accurate fruit classification, detecting shelf-life, identifying rotten fruits, and implementing standardized quality grading. Through automated processes and objective assessment, we strive to enhance food safety, reduce waste, and improve consumer satisfaction. The last paragraph of introduction chapter should contain an outline of the entire report. Summarize each chapter in one line to make the last paragraph.

1.2 Goals and Objectives

Our goal is to develop a mobile application that utilizes image recognition technology to empower users to make informed decisions when purchasing fruits, thereby reducing food waste and ensuring access to the highest quality produce.

Implement image recognition algorithms that can identify signs of rot, discoloration, mold, or texture irregularities when users point their smartphone cameras at fruits. Develop algorithms to analyze factors like fruit appearance, temperature, and handling conditions to estimate the remaining shelf life of fruits, providing valuable information for farmers, distributors, and retailers to optimize supply chain logistics and reduce spoilage.

Create a standardized system for categorizing fruits into different quality grades based on parameters such as appearance, firmness, and aroma, enabling users to distinguish between the healthiest, freshest fruits and those that are overripe or damaged.

Design the application with an intuitive user interface that is easy to navigate and understand, ensuring accessibility for a wide range of users including farmers, wholesalers, retailers, and consumers. Provide pricing information for different grades of fruit to enable users to make informed purchasing decisions based on their preferences and budget constraints, promoting fair pricing practices and fostering trust in the market.

Your Project Title Here 4

1.3 Scope of the Project

Users can point their smartphone camera at a fruit to determine its freshness. Using image recognition technology, the app can identify signs of rot, such as discoloration, mold, or texture irregularities. This feature helps consumers make informed decisions when purchasing fruits, reducing food waste and ensuring they get the best quality produce.

By analyzing factors like the fruit's appearance, temperature, and handling conditions, the app can estimate its remaining shelf life. This information is valuable for farmers, distributors, and retailers to manage inventory effectively, reducing spoilage and optimizing supply chain logistics.

The application can categorize fruits into different quality grades based on various parameters like appearance, firmness, and aroma. Users can easily distinguish between the healthiest, freshest fruits and those that are overripe or damaged. This feature empowers consumers to make healthier choices and helps suppliers maintain consistent quality standards.

User-Friendly Interface: The app is designed with simplicity and ease of use in mind. Intuitive controls and clear visual indicators make it accessible to a wide range of users, including farmers, wholesalers, retailers, and consumers. This ensures widespread adoption and maximum impact across the agriculture and fruit-buying communities. In addition to quality assessment, the app provides pricing information for different grades of fruit. Users can compare prices across various quality levels and make purchasing decisions based on their preferences and budget constraints. This transparency benefits both buyers and sellers by promoting fair pricing practices and fostering trust in the market.

1.4 Summary

Our project aims to revolutionize fruit classification, shelf-life detection, and quality grading through advanced technology, specifically leveraging artificial intelligence and computer vision. By addressing key challenges in agriculture and food industries, we seek to enhance food safety, reduce waste, and improve consumer satisfaction. The objectives include developing accurate fruit classification systems, detecting shelf-life, identifying rotten fruits, and implementing standardized quality grading. Through automated processes and objective assessment, our approach aims to provide a comprehensive solution to modernize fruit quality assessment and positively impact the entire fruit supply chain.

Chapter 2:

Literature Review

Your Project Title Here

Literature Review

2.1 Introduction

The literature review explores existing research and technologies relevant to fruit classification,

shelf-life detection, and quality grading. Various studies have highlighted the importance of

accurate fruit assessment for ensuring food safety, reducing waste, and enhancing consumer

satisfaction. Research in fruit classification has focused on both traditional methods, such as

manual sorting based on visual inspection, and modern techniques, including computer vision

and machine learning algorithms. These technologies enable automated classification of fruits

based on factors such as size, shape, color, and texture, leading to increased efficiency and

consistency in sorting processes.

In the realm of shelf-life detection, numerous studies have investigated factors influencing fruit

spoilage and decay, including temperature, humidity, handling practices, and storage

conditions. Advanced sensor technologies and predictive modeling approaches have been

developed to estimate the remaining shelf life of fruits, enabling farmers, distributors, and

retailers to optimize inventory management and reduce losses due to spoilage.

One of the key challenges faced in fruit quality assessment is the subjective nature of traditional

methods, which rely heavily on human judgment and are susceptible to biases and errors. Additionally, factors such as variability in fruit characteristics, environmental conditions, and

handling practices further complicate the assessment process, leading to inefficiencies and

inaccuracies in fruit sorting and grading.

Another critical issue is the lack of standardized grading systems across different regions and markets, resulting in discrepancies in quality standards and pricing practices. This inconsistency hampers transparency and fairness in the marketplace, leading to challenges for both producers and consumers in assessing the true value and quality of fruits.

Furthermore, the limited ability to accurately predict the shelf life of fruits poses significant challenges for farmers, distributors, and retailers in managing inventory and minimizing losses due to spoilage. Without reliable methods for shelf-life detection, stakeholders are often forced to rely on conservative estimates or manual inspections, which may result in suboptimal decisions and increased food waste.

Addressing these challenges requires innovative solutions that leverage advanced technologies, such as artificial intelligence and computer vision, to automate fruit quality assessment processes. By developing robust algorithms and systems for fruit classification, shelf-life detection, and quality grading, we can enhance efficiency, accuracy, and transparency across the entire fruit supply chain, ultimately improving food safety, reducing waste, and enhancing consumer satisfaction.

2.3 Detailed Literature Review

2.3.1 Definitions

A Detailed Literature Review for fresh and rotten fruit detection involves an extensive examination of existing research, studies, and methodologies about the identification and differentiation of fresh and rotten fruits using various techniques, including but not limited to artificial intelligence, computer vision, spectroscopy, and sensor technologies. This type of literature review aims to comprehensively analyze the state-of-the-art methods, challenges, and advancements in the field to inform the development of effective and accurate detection systems.

Review of Detection Techniques: An overview of different techniques used for fresh and rotten fruit detection, such as visual inspection, spectroscopic analysis, chemical sensors, and imaging technologies.

Analysis of AI and Computer Vision Approaches: Examination of AI and computer vision algorithms employed for automated fruit quality assessment, including image recognition, pattern recognition, and machine learning techniques.

Your Project Title Here 8

Comparative Analysis of Methods: Comparative analysis of the strengths, limitations, and performance metrics of different detection methods in terms of accuracy, speed, scalability, and practicality for real-world applications.

Accuracy: Investigation of factors influencing the accuracy and reliability of fresh and rotten fruit detection, including environmental conditions, fruit varieties, storage conditions, and sample preparation techniques.

2.3.2 Related Research Work 1

In Fresh and Rotten Fruits Classification Using CNN and Transfer Learning the classification of fresh and rotten fruits holds significant importance in agricultural fields, as it directly impacts food safety, quality assurance, and consumer satisfaction. In recent years, there has been a growing interest in leveraging deep learning models, particularly convolutional neural networks for automating fruit classification tasks.

In our work, we introduced a novel CNN-based model tailored specifically for the classification of fresh and rotten fruits. We focused on building transfer learning models, including VGG16, VGG19, MobileNet, and Xception, and compared their accuracies against our proposed CNN model. Additionally, we investigated the effects of different hyperparameters such as batch size, number of epochs, optimizer, and learning rate on model performance.

Our results demonstrated that the proposed CNN model outperformed transfer learning models in classifying fresh and rotten fruits, achieving a remarkable accuracy of 97.82%. This underscores the effectiveness of CNNs in automating the fruit classification process and reducing human errors associated with manual inspection. By leveraging convolutional neural network models, our approach streamlines the classification process, enhances accuracy, and improves efficiency in fruit quality assessment tasks.

Previous research in this domain has also explored the application of deep learning techniques for fruit classification. Studies have investigated various CNN architectures, optimization strategies, and dataset preprocessing techniques to achieve accurate and reliable classification results. Additionally, researchers have explored the use of alternative imaging modalities such as hyperspectral imaging and multispectral imaging for fruit quality assessment.

Overall, the development of CNN-based models for fruit classification represents a significant advancement in agricultural technology, offering potential benefits for farmers, distributors, retailers, and consumers. By automating the classification process and improving accuracy, these models contribute to enhancing food safety, reducing waste, and promoting sustainable agricultural practices.

2.3.3 Related Research Work 2

In An Advanced Method of Identification Fresh and Rotten Fruits using Different Convolutional Neural Networks fruit classification plays a pivotal role in various industries, facilitating efficient inventory management, pricing strategies, and quality assurance processes. The ability to accurately classify fruits not only aids vendors in supermarkets in identifying fruit species but also influences pricing decisions based on quality. Moreover, fruit classification systems are essential for ensuring the timely export of fresh fruits, as failure to do so can lead to economic losses.

In recent years, there has been a growing interest in developing fruit classification systems that leverage machine learning and computer vision technologies. These systems have the potential to streamline fruit classification processes and reduce reliance on human labor, particularly in the agriculture sector. By automating the classification of fresh and rotting fruits, these systems can improve efficiency, reduce costs, and enhance the overall quality of produce.

Previous research has demonstrated the effectiveness of machine learning models, particularly convolutional neural networks in fruit classification tasks. Studies have explored various CNN architectures, dataset sizes, and preprocessing techniques to achieve accurate classification results. Additionally, researchers have investigated the integration of fruit classification systems into autonomous agricultural robots and smartphone applications, further expanding their utility across different domains.

Your Project Title Here

2.4 Literature Review Summary Table

Sr.no Author Work Publish date

1 Reka, S.S., Bagelikar, A., Venugopal, P., Ravi, V. and Devarajan, H.

Deep Learning-

Based Classification of Rotten Fruits and Identification of Shelf Life.

30 January 2024

2 Jana, S., Parekh, R., & Sarkar, B.

Detection of Rotten Fruits and Vegetables Using Deep Learning. Computer Vision and Machine Learning in Agriculture

2021

3 Miah, M. S., Tasnuva, T., Islam, M., Keya, M., Rahman, M. R., & Hossain, S. A(IEEE)

An advanced method of identification fresh and rotten fruits using different convolutional neural networks

2021

4 Zhu, Z., Zhao, Y., Guo, Y., Zhang, R., Pan, Y., & Zhou, T.

A novel additional carbon source derived from rotten fruits: Application for the denitrification from mature landfill leachate and evaluation the economic benefits.

2021

5 Palakodati, S. S., S. S., Chirra, V., R. R., Yakobu, D., & Bulla, S

Fresh and Rotten Fruits Classification Using CNN and Transfer Learning.

12 October 2020

6 Nosseer, Ann; Ahmed, Seif Eldin Ashraf

Automatic Classification for Fruits' Types and Identification of Rotten Ones using k-NN and SVM.

2019

2.5 Research Gap

While several mobile applications exist for fruit detection and identification, there are notable research gaps in the functionality and capabilities of these apps:

Lack of Grading Feature: The majority of existing apps focus solely on fruit detection, with limited or no functionality for grading fruits based on quality attributes such as ripeness, freshness, or appearance. This gap suggests a need for mobile applications that can provide comprehensive grading capabilities to assist users in selecting the highest quality fruits.

Limited Automation for Rotten/Fresh Detection: While some apps offer detection of rotten or fresh fruits, the process often requires manual input or subjective assessment from the user. There is a gap in the development of fully automated systems that can accurately and reliably distinguish between rotten and fresh fruits in real-time, without user intervention.

Integration of Prediction Models: While a few apps offer prediction features for fruit shelf life or quality, there is a gap in integrating predictive models directly into detection and grading functionalities. Mobile applications that seamlessly combine detection, grading, and predictive capabilities could provide users with more actionable insights and decision-making support.

Variability in Accessibility and Pricing: Existing apps vary in terms of accessibility and pricing models, with some being free while others are paid. However, there is a lack of consistency in the features and quality offered across both free and paid apps. This gap highlights the need for standardized pricing models and clearer differentiation between free and paid versions based on functionality and value-added features.

Your Project Title Here

SR App Name Paid / Free Detection Grading Rotten / Fresh

01 Fruit Identifier paid ✓ × ×/×

02 Fruit name

with picture Free ✓ × ×/×

03 Fresh Fruit Detector Paid ✓ × ×/×

04 Fruit vegetable snap Free / Paid ✓ × ×/×

05 Fruit life-time

Prediction Free/Paid ✓ √ √/√

Table 2

2.6 Problem Statement

The presence of rotten fruits poses a significant risk to food safety and public health. Rotten fruits can harbor harmful bacteria, molds, and other microorganisms that have the potential to cause food poisoning and other illnesses in consumers. When fruits begin to rot, they undergo chemical and biological changes that create an ideal environment for the growth and proliferation of pathogens.

Consuming rotten fruits contaminated with pathogenic microorganisms can lead to a range of adverse health effects, including gastrointestinal infections, nausea, vomiting, diarrhea, and in severe cases, more serious complications such as dehydration and organ failure. Infants, young children, the elderly, and individuals with weakened immune systems are particularly vulnerable to the health risks associated with consuming contaminated food.

Furthermore, the presence of rotten fruits in the food supply chain can have broader economic

and societal implications. Contaminated fruits can result in food recalls, market withdrawals,

and loss of consumer confidence, leading to financial losses for producers, distributors, and

retailers. Additionally, outbreaks of foodborne illnesses linked to rotten fruits can strain

healthcare systems and impose significant burdens on public health resources.

Your Project Title Here 14

Chapter 3:

Requirement and desig[unreadable]

Requirements and Design

In this chapter, we discuss all the non-functional and functional requirements of fresh and rotten fruit detection. Before that, we will discuss all the problems statement that we have found while researching the project idea. Fresh and rotten fruit detection withholds many functional requirements. These requirements are gathered through various requirement-gathering techniques involving Brainstorming, Interviewing, and Observing. The non-functional requirements are drawn by observing the gathered requirements and type of our system.

3.1 Requirements

3.1.1 Requirement Elicitation Techniques:

Different Requirement Elicitation Techniques were used to gather and review different opinions of customers. This has helped us produce a clear straight path in developing an application that will be helpful to most customer demand.

3.1.1.1 Existing system

We study the existing systems to know that what kind of features present in them and how much they are useful for patients. Most of the system provides essential feature but some were not properly addressed. Many gaps were identified which led us to create an app that will be made according to the customer's demand.

3.1.1.2 Brainstorming

Helped us bring possible features to reality after reading and analyzing different systems and through constant research on increasing the efficiency of the system and how we can integrate an algorithm that provides accurate results.

3.1.1.3 Interviews

Our vital source for gathering requirements, we met different Eye doctors from our city and inquired about different problems they face. They helped us in Elements Descriptions understand the whole process of different eye diseases and their medication and process of treatment.

Your Project Title Here 16

3.1.1.4 Wire Framing

We created a wireframe to help us understand the requirements and get consensus on the workflow. Complete system wireframes allowed us to anticipate the user interface. The technology we used for designing wireframes is Figma.

3.2 Functional Requirements

The functional requirements of the fresh and rotten fruit AI system outline the specific features and functionalities essential for the system to effectively fulfill its purpose and meet the needs of its users. These requirements describe the desired behaviors and interactions of the system, ensuring that it provides a seamless and user-friendly experience.

3.2.1 Functional Requirements

FR.1: Users should be able to create an account and login to the app.

FR.2: Users should be able to detect fruit through pic.

FR.3: Users should be able to check the result.

FR.4: Users shall be able to provide feedback on the app

FR.5: User should be able to check fruit life.

FR.6: User should be able to logout.

3.2.2 Non-Functional Requirements

N-FR.1: The app shall be designed to handle a large number of users.

N-FR.2: The app shall be compatible with multiple devices.

N-FR.3: The app shall have a user-friendly interface, with easy navigation design.

3.2.3 Hardware and Software Requirements

To use the virtual psych app, users need a device that meets the minimum hardware and software requirements. The app is designed to be lightweight, which means it can run smoothly on most modern smartphones, tablets and browser.

Hardware Requirements

HR.1: Minimum 2GB RAM (recommended 4GB or higher)

HR.2: Minimum 1GHz processor (recommended 1.8GHz or higher)

Software Requirements

SR.1: (Operating system) Android 5.0 or higher / iOS 10 or higher

SR.2: (Internet connection) Minimum 3G (recommended 4G or higher)

3.3 Proposed Methodology

3.3.1 Data Collection

Gather a comprehensive dataset of fruit images containing examples of both fresh and rotten fruits. Include a diverse range of fruit types and conditions to ensure the model's robustness and generalization ability. Annotate the dataset to indicate the freshness status of each fruit image fresh or rotten.

3.3.2 Preprocessing

Perform data preprocessing techniques such as resizing, normalization, and augmentation to enhance the quality and diversity of the dataset. Apply methods to address common challenges in fruit image analysis, such as background clutter, lighting variations, and occlusions.

3.3.3 Model Selection

Explore various deep learning architectures suitable for image classification and object detection tasks, such as convolutional neural networks (CNNs) and object detection frameworks like YOLO or Faster R-CNN. Select a model or combination of models that offer high accuracy and efficiency in detecting fresh and rotten fruits.

Your Project Title Here 18

3.3.4 Model Training:

Split the annotated dataset into training, validation, and testing sets to train and evaluate the performance of the models. Fine-tune the selected model on the fruit image dataset to optimize detection accuracy and minimize false positives/negatives. Experiment with transfer learning techniques using pre-trained models to leverage knowledge from large-scale image datasets.

3.3.5 Integration of Freshness Detection:

Implement algorithms for detecting freshness indicators in fruit images, such as color changes, texture irregularities, and presence of mold or decay. Incorporate feature extraction and classification methods to differentiate between fresh and rotten fruits based on visual cues. Ensure that the detection process is efficient, scalable, and capable of handling real-time inputs from various sources.

3.3.6 Deployment and Integration:

Develop a user-friendly interface for the freshness detection system, allowing users to upload images and receive real-time feedback on the freshness status of fruits. Integrate the trained model into the backend of the system, ensuring scalability, reliability, and efficiency in processing image inputs. Deploy the finalized freshness detection system for practical applications in agricultural production, food processing, retail, and consumer services.

System Architecture

Use Cases

User use case diagram

forget password

Detect fruit

View result

view profile

<<include>>

edit profile

update profile

logout

User

1.1 Sample Use Case Name Here

Name Sample Use Case Name Here

Actors Admin, Business Owner, Store Manager

Summary The user shall provide their email and password on the login form and after successful verification, redirect the user to the home page.

Pre-Conditions The user must be in the databse records either added by any of the authorized users or added manually by a developer.

The user must not already be logged in.

Post-Conditions The user’s session is successfully established and shall be redirected to the home page.

Special Requirements None

Basic Flow

Actor Action | System Response

1 The user opens the login page. | 2 The login page is displayed asking for

Your Project Title Here

3 The user enters valid email and password.

4 The system verifies the email and password, establishes a session for the user and redirects the user to the home page.

email and password.

Alternative Flow

3 The user enters invalid email or password.

4-4-A The system responds with an error message: Incorrect email or password entered.

Database Design

Firebase is a NoSQL database. There aren't any tables or rows like in a SQL database. Rather, information is kept in papers that are arranged into collections. Therefore, instead of designing an Entity Relationship Diagram, we have designed a Data Model Diagram to represent the collections and the document visually made inside those collections. Collections must be used to hold all papers.

Sequence diagram

User

system

Database

1:Click to sign up button

2: Display sign up page

Loop

3:Enter sign up credentials

4: verify enter credential

Authenticating user data and save in database

Click to sign up

alt

Your Project Title Here 22

User

system

Database

1:Click to login button

2: Display login page

3:Enter login credentials

4: verify enter credential

Loop

alt

Click to login

Check user credentials

Email & password=match

valid input

invalid input

1:Click to forget password button

2: Display forget password page

3:Enter email address

4: verify email

Click to rest password

Click to sign up

Email found

checking user credentials

valid input

reset email link sent

invalid input

rest email link not sent

enter new password

Re-enter new password

confirm reset

update user password

update password

password Update

Your Project Title Here

User

system(app)

Database

1:Click to take image button

2: Display camera

3:Take a clear image

Retake if image is blur

Click to submit

Save image path

saved successfully

alt

valid input

image taken successfully

invalid input

image taken unsuccessfully

click to log out

Display confirm message

Select confirm

Log out Successfully

Log out unsuccessfully

Select cancel

Alt

Valid

Invalid

Select confirm

Log out successfully

Log out unsuccessfully

Select cancel

CNN Architecture diagram

Input

Convolution

Pooling

Fully Connected

Output

Feature Extraction

Classification

Your Project Title Here

Implementation and Test Cases

For each chapter provide a paragraph of introduction and in the end a paragraph of conclusions.

Implementation

Whatever implementation that you have done so far, please elaborate here.

Give clear details of the algorithms that were implemented along with the platform and the APIs which were used. For FYP-1, this chapter can be changed to description of prototype developed.

1.1.2 Implementation of First Component/Algorithm

Write implementation of first component of your system here.

Test case Design and description

This section will be added in FYP-II. Summarize the common attributes of test cases. This may include input constraints that must be true for every input in the set of associated test cases, any shared environmental needs, any shared special procedural requirements, and any shared case dependencies. The following scheme is recommended for describing test cases in detail.

1.1.3 Sample Test case No.1

Test Case ID: Reference Number

Test Date: Date

Test case Version: Version number

Use Case Reference(s):

Relation to use cases

Revision History: Refer to previous test case identity (if any)

Objective: Need and scope of the testing

Product/Ver/Module: Refer to overall system being built and the place of this test case in it.

Environment: Necessary and desired properties of the test environment. (hardware/software)

Assumptions: Assumptions that might affect the testing process.

Pre-Requisite: Necessary condition that needs to be fulfilled prior to the test case.

Step No. Execution description

Procedure result

Events being tested.

Mention software response.

Comments:

□ Passed □ Failed □Not Executed

1.1.4 Sample Test case No.2

Test Metrics

Summarize here the common ground of attributes of test case metrics.

1.1.5 Sample Test case Matric.No.1

Metric: Purpose

Number of Test Cases: Total number of test cases that you have developed for

your system.

Number of Test Cases Passed: The number of test cases that successfully passed

Number of Test Cases Failed: The number of test cases that failed

Test Case Defect Density: (No of test cases failed * 100)

No of test cases executed

Test Case Effectiveness: No of defects detected using test cases *100

Total number of defects detected

Traceability Matrix: Traceability is the ability to determine that each feature

has a source in requirements and each requirement has a

corresponding implemented feature.

1.1.6 Sample Test case Metric.No.2

1.1.7 Sample Test case Metric.No.3

Your Project Title Here 28

[1] P.M. Morse and H. Feshback, Methods of Theoretical Physics. New York: McGraw Hill, 1953. //Format for Book

[2] S.K. Kenue and J.F. Greenleaf, “Limited angle multifrequency diffraction tomography,” IEEE Trans. Sonics Ultrason., vol. SU-29, no. 6, pp. 213-2 17, July 1982. //Format for Journal Article

[3] B. Tsikos, “Segmentation of 3-D scenes using multi-modal interaction between machine vision and programmable mechanical scene manipulation,” Ph.D. dissertation, Univ. of Pennsylvania, BCE Dept., Philadelphia, 1987. [Add if applicable: University Microfilms, Inc., University of Michigan, Ann Arbor, Michigan.] //Format for Dissertation or thesis

[4] R. Finkel, R. Taylor, R. Bolles, R. Paul, and J. Feldman, “An overview of AL, programming system for automation,” in Proc. Fourth Int. Joint Conf Artif. Intell., pp. 758-765, Sept. 3-7, 1975. //Format for Proceedings paper

[5] “Technology threatens to shatter the world of college textbooks, The Wall Street Journal, vol 91, pp. A1, A8, June 1, 1993. //Format for Newspaper article

[6] R. Cox and J. S. Turner, “Project Zeus: design of a broadband network and its application on a university campus,” Washington Univ., Dept. of Comp. Sci., Technical Report WUCS-91-45, July 30, 1991. //Format for Technical Report

[7] M. Janzen, Instant Access Accounting. Computer software. Nexus Software, Inc IBM-PC, 1993. //Format for Software

[8] Fuminao Okumura and Hajime Takagi, “Maglev Guideway On the Yamanashi Test Line,” http://www.rtri.or.jp/rd/maglev2/okumura.html, October 24, 1998. //Format for World Wide Web (give author and title if named)

[9] “AT&T Supplies First CDMA Cellular System in Indonesia,” http://www.att.com/press/1095/951011.nsa.html, Feb 5, 1996. //Format for World Wide Web