Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

HANDWRITTEN TEXT RECOGNIZATION

A Project Report Submitted in fulfillment of the


partial
Requirements for the award of the degree of

BACHELOR OF TECHNOLOGY
In

COMPUTER SCIENCE AND ENGINEERING

By

K. SRAVANI (17001A0520)

D. HEMANTH KUMAR (17001A0534)

K. KIRAN KUMAR (18005A0502)

Under the guidance of

Dr. A.P. Siva Kumar M. Tech., Ph.D

ASSOCIATE PROFESSOR

HRUTEC

VERS
NGINE ERUNO ANANTAPun)

cOLLE GI

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY ANANTAPUR

COLLEGE OF ENGINEERING

(Autonomous)
ANANTHAPURAMU-515002

ANDHRA PRADESHH

2021
AWAHARLAL NEHRU TECHNOLoGICAL UNIVERSITY ANANTAPUR
COLLEGE OF ENGINEERING (AUTONOMOUS)
ANANTHAPURAMU-515002

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

ERST
T: KE,
pKGHEEPING) (ANATAPUR

COLLEGE

CERTIFICATE
This is to certify that the project entitled "HANDwRITTEN TEXT RECOGNIZATION" is a bonafide work

of K. Sravani, bearing Admission No: 17001A0520, D. Hemanth Kumar, bearing Admission No


17001A0534 and K. Kiran Kumar, bearing Admission No:18005A0502, is submitted to the faculty of

Computer Science and Engineering, in partial fulfillment of the requirements for the award of degree of
BACHELOR OF TECHNOLOGY in COMPUTER SCIENCE AND ENGINEERING from Jawaharlal
Nehru Technological University Anantapur College of Engineering (Auionomous), Ananthapuramu.

ollra
Signature of the GUIDE Signature of the HODD
Dr. A.P. Siva Kumar, Dr. K. Madhavi,

B.Tech., M.Tech., Ph. D., B.Tech., M.Tech., Ph. D.,


AssociateProfessor, AssociateProfessor & HOD,

Department of CSE, Department of CSE,


JNTUA College of Engineering, JNTUA College of Engineering,
ANANTHAPURAMU-515002. ANANTHAPURAMU-515002.
ABSTRACT

is the ability of computers to recognize human handwritten text.


The handwritten recognition
because handwritten Text are not perfect and can be made with many
It is a hard task for the machine
handwritten Text recognition is the solution to this problem which uses the image of
different flavors
Character and recognizes the Text present in the image.

handwritten word so that handwritten text can be translated to


This project seeks to classify a

words directly and


form. We used two main approaches to accomplish this task: classifying
a digital various
Convolutional Neural Network (CNN) with
segmentation. For the former, we
use
character
model that can accurately classify words. For the latter, we use Long Short
architectures to train a
convolution to construct bounding boxes for each character. We
with
term Memory networks (LSTM)
each word
CNN for classification, and then
reconstruct
segmented characters to a
then pass the

according to the results of classification and segmentation.


to extract the data from, so either create an app that lets you
The Vision API needs an image
app that uses the Camera APls to click a picture and use

upload images from the gallery or create an


it instead.

Camera APl's
I found this library to be pretty handy and easy to use instead ofthe framework

MatConvNet can be used to implement our model with CPU training as

We will also show how


is to create a model which can recognize the digits, we can

well as less training time. Though the goal


this work, we aim to learn and practically
extend it for letters and then a person's handwriting. Through
Neural Networks
apply the concepts of Convolutional

You might also like