Scribd
Upload
12 views4 pages

2021 22 CSE Handwritten Digit Recognition 4

Uploaded by

narenchitra21
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views4 pages

2021 22 CSE Handwritten Digit Recognition 4

Uploaded by

narenchitra21
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

AMAJOR PROJECT REPORT

ON

HANDWRITTEN DIGIT RECOGNITION"


AMajor Project report submitted in partial fulfillment of
requirementfor the award of the degree of
BACHELOR OF TECHNOLOGY
IN

COMPUTER SCIENCE AND ENGINEERING


BY
NAME REGISTER NUMBER

R. SAI LIKITHA 18091A05B4

Y. BHARGAVI 18091A0509
S. ANUSHA 18091A0503

G.SATYA SWETHA 18091A05C1

Under the guidance of


G.RAJASEKHAR REDDY M.Tech (Ph.D)
Assistant Professor of CSE Department

EDUCATIgh I0aPLAct

ESTD -1995
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
RAJEEV GANDHIMEMORIAL COLLEGE OF ENGINEERING
& TECHINOLOGY
(AUTONOMOUS)
Accredited by NAAC of UGC, New Delhi with 'A+ Grade
Approved by AlCTE, Afiliated to J.NT University Anantapur, Nandyal-5 18501
RUEEY GANDIII MEMORIAL COLLEGE OF ENGINEERING
& TECINOLOGY
(AUTONOMOUS)
Accredited by NAACof UGC, New Delhi with A+ Grade
Approved by AlCTE. Aliliated to J.N.T,University Anantapur, Nandyal-5 18501

OUCANON SOA PO

ESTD-1995

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIEICATE
This is to certify that R.SAI LIKITHA(18091A0SB4), Y. BHARGAVI(18091A0509),
S. ANUSHA (18091A0503), G. SATYA SWETHA(18091A05Cl)of B.Tech CSE final year
has carried out the project work on HANDWRITTEN DIGIT RECOGNITION" under the
esteemed guidance of G. RAJASEKHAR REDDY, Assistant Professor of CSE department,
for the partial fulfillment of the award of the degree of B.Tech in CSE in R.G.M.C.E.T.
Nandyal sa bonafide record of work done by them during the year 2021-2022.

Head of Dpartment: Project Guide:

Dr. K. Subba Reddy MTech, Ph.D. G. RAJASEKHAR REDDY M.Tech, (Ph.D)

Professor & HOD Assistant Professor


Department of C.S.E Department of C.S.E

Place: Nandyal Examiner:


Date:
ABSTRACT
HANDWRITTEN DIGIT RECOGNITION

Handwritten digit recognition is the ability of computers to recognize human handwritten


}ete tis a hardtask for the machine because handwritten digits are not perfect, vary from person
to person, and can be made with different sources like touch screens, images, etc. The main
obiective of this project is to predict the Telugu digits effectively. To implement this, we will use
CNN (convolutional neural networks). We will use different layers to achieve highly accurate
results.

In the previous model, they only considered English digits. But in this project, we consider
Telugu digits which are varying from English digits. Previously Telugu digits were used in
documents, vehicle number plates, etc. When we write in Telugu digits, it willdetect that particular
digit into its corresponding English digit. Using the dataset and compiling it with the CNN gives
the basic structure of my project development.
HANDWRITTEN DIGIT RECOGINITION

CHAPTER 10
CONCLUSION

Handwritten digit recognition has immense applications in the field of medical,


Many classifiers like KNN, SVM, CNN
banking, student management, taxation process, etc.
the review, CNN is providing
are used to identify the digit from the handwritten image. as per
better performance than others.
handwritten digits. Later it can be
Here we demonstrate a model which can recognize
extended for character recognition andreal-time person's handwriting. Handwritten digit
Intelligence and Computer Vision. As
recognition is the first step to the vast field of Artificial
The
proves to be far better than other classifiers.
seen from the results of the experiment, CNN
convolution layers and more hidden neurons. It
results can be made more accurate with more
typing.
can completely abolish the need for
for learning about neural networks
Digit recognition is an excellent prototype problem
advanced techniques of deep learning. In the future,
and it gives a great way to develop more
handwritten digit recognition system.
we are planning to develop a real-time
namely, hybrid CNN, viz., CNN-RNN
In the future, diferent architectures of CNN,
systems, can be investigated.
and CNN-HMM models, and domain-specific recognition
learning parameters, namely, the
Evolutionary algorithms can be explored for optimizing CNN
convolutional filters.
number of layers, learning rate, and kernel sizes of

Dept. of CSE, RGMCET, Nandyal


63

You might also like