Sign Language

Recognition System
Feasibility report
By
Shivam Agarwal
Abhishek Ganguly
Shuvadip Shaw
Atri Munshi
Contents
1. Introduction
1.1 Overview of the Project
1.2 Objective of the Project
1.3 Need for the Project
1.4 Overview of Existing Technologies and System
1.5 Scope of the Project
1.6 Deliverables

2. Feasibility Study
2.1 Technical Feasibility
2.2 Resource and Time Feasibility
2.3 Financial Feasibility
2.4 Risk Feasibility
2.5 Social/Legal Feasibility

3. System Requirements
3.1 Software Used
3.2 Platform and Tools Used

4. Software Life-Cycle
INTRODUCTION:
1.1 Overview of the project:
Sign language is the only tool of communication for the person who is not able to speak and hear
anything. Sign language is a boon for the physically challenged people to express their thoughts
and emotion. In this work, a novel scheme of sign language recognition has been proposed for
identifying the alphabets and gestures in sign language. With the help of computer vision and
neural networks we can detect the signs and give the respective text output. The gesture is a vital
and meaningful mode of communication for the visually impaired person. So here is the
computer-based method for regular people to understand what the differently-abled individual
is trying to say. In our system, the user will perform the hand gestures or signs by turning on their
camera, and the system will detect the sign and display it to the user. The goal of this project was
to build a neural network able to classify which letter of the Sign Language alphabet is being
signed, given an image of a signing hand. This project is a first step towards building a possible
sign language translator, which can take communications in sign language and translate them
into written and oral language. Such a translator would greatly lower the barrier for many deaf
and mute individuals to be able to better communicate with others in day to day interactions.
1.2 Objective of the Project:
The objective is motivated by the isolation that is felt within the deaf community. Loneliness and
depression exists in higher rates among the deaf population, especially when they are immersed
in a hearing world. Large barriers that profoundly a enact life quality stem from the
communication disconnect between the deaf and the hearing. Some examples are information
deprivation, limitation of social connections, and difficulty integrating in society.

1.3 Need for the Project:

Speech impaired people use hand signs and gestures to communicate. Normal people face
difficulty in understanding their language. Hence there is a need of a system which recognizes
the different signs, gestures and conveys the information to the normal people. It bridges the
gap between physically challenged people and normal people. CNN is very satisfactory at picking
up on design in the input image, such as lines, gradients, circles, or even eyes and faces. Image
processing algorithms along with neural networks is used to map the gesture to appropriate text
in the training data and hence raw images/videos are converted into respective text that can be
read and understood. Dumb people are usually deprived of normal communication with other
people in the society. It has been observed that they find it really difficult at times to interact
with normal people with their gestures, as only a very few of those are recognized by most
people. Since people with hearing impairment or deaf people cannot talk like normal people so
they have to depend on some sort of visual communication in most of the time. Sign Language
is the primary means of communication in the deaf and dumb community. As like any other
language it has also got grammar and vocabulary but uses visual modality for exchanging
information. The problem arises when dumb or deaf people try to express themselves to other
people with the help of these sign language grammars. This is because normal people are usually
unaware of these grammars. As a result it has been seen that communication of a dumb person
are only limited within his/her family or the deaf community. The importance of sign language
is emphasized by the growing public approval and funds for international project. At this age of
Technology the demand for a computer based system is highly demanding for the dumb
community. However, researchers have been attacking the problem for quite some time now
and the results are showing some promise. Interesting technologies are being developed for
speech recognition but no real commercial product for sign recognition is actually there in the
current market.

1.4 Overview of Existing Technology and System:

There are similar works that are implemented in the domain of sign language recognition.The
summaries of each of the project works are mentioned below:
❖ A Survey of Hand Gesture Recognition Methods in Sign Language Recognition
 ❖ Communication between Deaf-Dumb People and Normal People
❖ A System for Recognition of Indian Sign Language for Deaf People using Otsu’s
Algorithm
❖ Intelligent Sign Language Recognition Using Image Processing
❖ Sign Language Interpreter using Image Processing and Machine Learning
❖ Hand Gesture Recognition based on Digital Image Processing using MATLAB
Our proposed system is sign language recognition system using convolution neural networks
which recognizes various hand gestures by capturing video and converting it into frames. Then
the hand pixels are segmented and the image it obtained and sent for comparison to the trained
model. Thus our system is more robust in getting exact text labels of letters.

1.5 Scope of the Project:

There is high scope of this project in this digital world where AI is taking care of everything with
very low cost. Nowadays, applications need several kinds of images as sources of information for
elucidation and analysis. Several features are to be extracted so as to perform various applications.
When an image is transformed from one form to another such as digitizing, scanning, and
communicating, storing, etc. degradation occurs. Therefore, the output image has to undertake a
process called image enhancement, which contains of a group of methods that seek to develop the
visual presence of an image. Image enhancement is fundamentally enlightening the
interpretability or awareness of information in images for human listeners and providing better
input for other automatic image processing systems. Image then undergoes feature extraction
using various methods to make the image more readable by the computer. Sign language
recognition system is a powerful tool to prepare an expert knowledge, edge detect and the
combination of inaccurate information from different sources, the intend of convolution neural
network is to get the appropriate classification

1.6 Deliverables:
A GUI based software system. This contains a central database and functionalities for various
users datas. Since many number of people are involved, different result and GUIs would be
provided to a different users.
Feasibility Study
2.1 Technical Feasibility:
Feature Extraction and Representation : The representation of an image as a 3D matrix having
dimension as of height and width of the image and the value of each pixel as depth ( 1 in case
of Grayscale and 3 in case of RGB ). Further, these pixel values are used for extracting useful
features using CNN.

• Artificial Neural Networks: Artificial Neural Network is a connections of neuron,

replicating the structure of human brain. Each connection of neuron transfers
information to another neuron. Inputs are fed into first layer of neurons which
processes it and transfers to another layer of neurons called as hidden layers. After
processing of information through multiple layers of hidden layers, information is
passed to final output layer.
• Convolution Neural Networks: Unlike regular Neural Networks, in the layers of CNN, the
neurons are arranged in 3 dimensions: width, height, depth. The neurons in a layer will
only be connected to a small region of the layer (window size) before it, instead of all of
the neurons in a fully-connected manner.
• Moreover, the final output layer would have dimensions (number of classes), because
by the end of the CNN architecture we will reduce the full image into a single vector of
class scores.
SLR is a complete GUI based application. The main technologies and tools that are associated
with SLR are

• OpenCV
• Tkinter
• Dlib
• Keras
• AI
• Numpy
• Tensorflow
• CNN
Each of the technologies or packages are freely available and the technical skills required are
manageable. Time limitations of the product development and the case of implementing using
these technologies are synchronized.
Initially the GUI will be hosted in a free web hosting space, but for later implementations it will
be hosted in a paid web hosting space with a sufficient bandwidth. From these, it is clear that
project SLR is technically feasible.
2.2 Resource and Time Feasibility
Resources that are required for the project includes:
• Programming Device (Laptop)
• Hosting Space (freely available)
• Programming Tools (freely available)
• Programming individuals
So, it’s clear that SLR has required resource feasibility.

2.3 Financial Feasibility

Being a GUI application SLR will have an associated exe file which required to be hosted.
Bandwidth required for the system is low. It will follow the freeware software standards. No
cost will be charged from potential customers. Bug fixes and maintenance task will have
additional costs. At the initial stage the potential customers are NGOs, social welfare
community. Beside the associated code, there will be many benefits for the customers.
Especially the extra effort that is associated in train and learn of deaf people will not be
required, it’s fully automated. Therefore, it’s financially feasible.
2.4 Risk Feasibility:
Risk associated with size
• Estimated size of the product in line of codes:
Being a GUI application with many number of users of
different backgrounds . SLR will contain significant amount of code
lines. As the system doesn’t contain any multimedia aspect , the file
sizes and the complete project size will not exceed 200Mb.
• Estimated size of product in number of the programs:
Though the application supports many packages and
libraries, it will be constructed as a single GUI application with a single
login page rather then having many number of the sites for different
users. Depending on the access rights, the contents will be showed or
hidden.
• Does the environment make use of a database or repository?
This is a database oriented system that will use .
Are all the software tools integrated with one another
Main deliverables will be packaged under a single project.
• Process issue risks
SLR will follow the software development Process. This
provides the flexibility to accommodate changing software
requirements of SLR.
• Technical issue risk
Are specific conventions for code documentation defined and
used Software code will be freely available and the code
documentation will be provided.
 • Is the technology to be built new?
All the technologies are very well established and old enough (but
not obsolete).
• Do the system requirements demand the creation of new
algorithms , input or output technology?
SLR will have several algorithms to generate quizzes, making of
essay type questions and to generate statistical distributions.

2.5 Social/Legal Feasibility:

SLR uses freely available development tools and provide the system
as an open source system, Only the maintenance cost will be charged
from potential customers.
Python packages and libraries that are used in this system are free
source libraries.
Since this new system eliminates the effort to make statistical
distribution, it will have a great impact in a social equality and
community system.

3. System Requirements:
Software requirements
Operating System: Windows, Mac, Linux
SDK: OpenCV, TensorFlow, Keras, Numpy
IDE: Pycharm or Jupyter Notebook

Hardware Requirements
Camera: Good quality,3MP
 Ram: Minimum 8GB or higher
GPU: 4GB dedicated
Processor: Intel Pentium 4 or higher
HDD: 10GB or higher
Monitor: 15” or 17” colour monitor
Mouse: Scroll or Optical Mouse or Touch Pad
Keyboard: Standard 110 keys keyboard

4. SOFTWARE LIFE CYCLE:

The waterfall model is a classical model used in the system development life cycle to create a
system with a linear and sequential approach. It is termed a waterfall because the model
develops systematically from one phase to another in a downward fashion. The waterfall
approach does not define the process to go back to the previous phase to handle changes in
requirements. The waterfall approach is the earliest approach that was used for software
development.
Decision Tree and Table:
DFD: