Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 8

Software Requirements Specification

Code-RCA-552

For

Submitted towards Partial Fulfillment for the Requirements of Fifth Semester of

MASTER OF COMPUTER APPLICATION

Prepared by -Aman Saxena


1900360149008

Supervised by
Dr.Nipendra Dwivedi Sir

Department of Computer Application


Institute of Management Studies, Ghaziabad
Dr. A.P.J Abdul Kalam Technical University,
Lucknow, Uttar Pradesh.
Session-2020-21
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page ii

Table of Contents
Table of Contents...........................................................................................................................ii
Revision History.............................................................................................................................ii
1. Introduction..............................................................................................................................1
1.1 Purpose...........................................................................................................................................1
1.2 Document Conventions...................................................................................................................1
1.3 Intended Audience and Reading Suggestions.................................................................................1
1.4 Product Scope.................................................................................................................................1
1.5 References......................................................................................................................................1
2. Overall Description..................................................................................................................2
2.1 Product Perspective.........................................................................................................................2
2.2 Product Functions...........................................................................................................................2
2.3 User Classes and Characteristics.....................................................................................................2
2.4 Operating Environment...................................................................................................................2
2.5 Design and Implementation Constraints.........................................................................................2
2.6 User Documentation.......................................................................................................................2
2.7 Assumptions and Dependencies......................................................................................................3
3. Other Nonfunctional Requirements.......................................................................................4
3.1 Performance Requirements.............................................................................................................4
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 3

1. Introduction
1.1 Purpose
Handwritten digit recognition has gained so much popularity from the
aspiring beginner of machine learning and deep learning to an expert who has
been practicing for years. Developing such a system includes a machine to
understand and classify the images of handwritten digits as 10 digits (0–9).
1.2 Document Conventions
The document strictly follows the IEEE standard format and no other formatting is
done in the document.

1.3 Intended Audience and Reading Suggestions

This SRS is an easy guide for the developers (us), the professor who can act
as our client and the project managers. It will help in building the application
with the flow and also provide a clear vision of the application before we
actually start making the application. Images of digits were taken from a
variety of scanned documents, normalized in size and centered. This
makes it an excellent dataset for evaluating models, allowing the
developer to focus on the machine learning with very little data cleaning
or preparation required.

It is a digit recognition task. As such there are 10 digits (0 to 9) or 10


classes to predict. Results are reported using prediction error, which is
nothing more than the inverted classification accuracy.

Excellent results achieve a prediction error of less than 1%. State-of-the-


art prediction error of approximately 0.2% can be achieved with large
Convolutional Neural Networks.
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 4

1.4 Product Scope

 Extend the model to work on MNIST DATASET.


 Increase the accuracy further by implementing more number
of hidden layers and/or eposchs
 Detect custom hands written digits.
 Use CNN with less layers to get better accuracy

1.5 References
[1] Hand Written Digit Recognition Using TensorFlow and Python; Shekhar
Shiroor Department of Computer Science College of Engineering and
Computer Science California State University-Sacramento Sacramento, CA
95819-6021, USA

[2]. Analogizing Time Complexity of KNN and CNN in Recognizing


Handwritten Digits; Tanya Makkar & Yogesh Kumar Department of ECE,
Amity School of Engg. and Technology, Amity University Uttar Pradesh,
Noida, India; Ashwani Kr Dubey Department of ECE, Amity School of Engg.
and Technology, Amity University Uttar Pradesh, Noida, India; Álvaro Rocha
Department of Informatics Engineering, University of Coimbra Portugal;
Ayush Goyal Electronics & Communication Engineering, Texas A&M
University – Kingsville

[3]. Handwritten Digits Recognition with Artificial Neural Network; Kh


Tohidul Islam, Ghulam Mujtaba, Dr. Ram Gopal Raj, Henry Friday Nweke

[4]. https://www.tensorflow.org.>

2. Overall Description
2.1 Product Perspective
HWR is first of its kind and doublessly first open source endeavor to perceive
the essayist in view of his composition as every individual has an alternate
written by hand style. The point Handwritten Digits Recognition based
Multifeatures of te venture would to add to a framework which can be
utilized effectively wverywhere associations .
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 5

2.2 Product Functions


The real capacity of HWRC is to perceive an essayist from the poll of
auther.Individual confirmation is essential at numerous associations this
venture might be utilized as a part of such places. Individual recognizable
proof is likewise imperative in measurable divison.

2.3 User Classes and Characteristics


1. Large organizations
3.Academic Organization.

2.4 Assumptions and Dependencies


The framework must be prepared completely before use and client knows
the framework particular.When framework is prepared,beforebleaving you
are requroed to spare the framework,so the framework stacked for further
use.also the upgraded quality.

3. Other Nonfunctional Requirements


3.1 Performance Requirements
Execution relying upon the connection high PC execution might one or more
a greater amount of the accompanying: Short reaction time for a given bit of
work.Execution is described by the measure of valuable work achived by a
PC framework or PC system contrasted with the time and assest utilized.

4. Other Requirements
Reliablity:
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 6

Unwavering quality is a property of any PC related part that reliably


performs as indicated by its determinations.It has for some time been
viewed as one of three related qualities that should be considered
when making,purchasing or utilizing a PC item or part.
Availability:
In PC framework and system administration,accessibility is a general
terms that is utilized to depict the measure of time over one-year
period that the framework assets is accessible in the wake of part
disappointments in the system.A framework constantly accessible with
its all assets are viewed as fruitful.
METHADOLOGY:
We added to a framework for manging such issue. The framework began by
obtaining a picture containing digits,this picture was digitized utilizing some
optical gadgets and in the wake of applying a few improvements alterations
to the digits inside of the puctures.

DFD:
View Panel

show

User
etEnvoirem

Enter
Or Didit
Character

Wrong character

Configratuation information
Recognise

Digits
Character

Spell
Checker View Output Display
Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 7

USE CASE DIAGRAM:

Upload Image User

Cancel

Initlize convert image gray scale

System

Pre-Process Image normalization

State Diagram:

Scans documents

Administrator

Read images

Stores the images


Software Requirements Specification for <Hand Written Digits Recognition Using Machine Learning>
Page 8

You might also like