Scribd
Upload
91 views

Handwritten Text Recognition

Uploaded by

Sundas Noreen
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
91 views

Handwritten Text Recognition

Uploaded by

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

ARTIFICIAL INTELLIGENCE

PROJECT PROPOSAL

Title of the Project:


Handwritten Text Recognition

About:
Handwritten text (digit and character) recognition is the ability of a computer to recognize the
human handwritten text from different sources like images, papers or touch screens and classify
them into predefined classes of digits and characters.

Objective:
To design a handwritten text recognition system that not only detects scanned images of
handwritten text but also allows writing on the screen with the help of an integrated GUI for
recognition.

Problems Faced:
In Handwritten text recognition, we face many challenges because of different styles of writing
of different peoples. It is a hard task for the machine because handwritten text is not perfect and
can be made with many different flavors. Another area raising digit recognition issues are the
similarities between some digits: 3 and 8, 0 and 8, 5 and 6, 2 and 7 etc. and several alphabets.

Applications:
Text recognition has many applications like number plate recognition, postal mail sorting, bank
check processing, scanning books, making digital records etc.

Datasets:
Handwritten character recognition is an expansive research area that already contains detailed
ways of implementation which include major learning datasets, popular algorithms, features
scaling and feature extraction methods.
1. A-Z Handwritten Alphabets Dataset contains 37000+ English alphabets in 28x28 pixels,
each alphabet in the image is fitted to 2020-pixel box.
2. MNIST dataset (Modified National Institute of Standards and Technology database) is
probably one of the most popular datasets among machine learning and deep learning
enthusiasts. MNIST dataset is the subset of the NIST dataset which is a combination of
two of NIST’s databases: Special Database 1 and Special Database 3. Special Database 1
and Special Database 3 consist of digits written by high school students and employees of
the United States Census Bureau, respectively. The MNIST dataset contains 60,000
training images of handwritten digits from zero to nine and 10,000 images for testing. So,
the MNIST dataset has 10 different classes. The handwritten digits images are
represented as a 28×28 matrix where each cell contains grayscale pixel value.

Figure 1 - Bar graph illustrating the MNIST handwritten digit training dataset
(Label vs Total number of training samples).

Figure 2 - Plotting of some random MNIST Handwritten digits.


Datasets at:
https://www.kaggle.com/sachinpatel21/az-handwritten-alphabets-in-csv-format
https://www.nist.gov/itl/products-and-services/emnist-dataset

Algorithm to be used:
Convolutional Neural Networks (CNN) will be used. CNN is a deep learning algorithm that is
widely used for image recognition and classification. It is a class of deep neural networks that
require minimum pre-processing. It inputs the image in the form of small chunks rather than
inputting a single pixel at a time, so the network can detect uncertain patterns (edges) in the
image more efficiently.

CNN contains 3 layers namely, an input layer, an output layer, and multiple hidden layers which
include Convolutional layers, Pooling layers (Max and Average pooling), Fully connected layers
(FC), and normalization layers.

CNN uses a filter (kernel) which is an array of weights to extract features from the input image.
CNN employs different activation functions at each layer to add some non-linearity. As we move
into the CNN, we observe the height and width decrease while the number of channels increases.
Finally, the generated column matrix is used to predict the output.

Figure 3 - This figure shows the architectural design of CNN layers in the form of a flow chart.
Implementation:
The implementation of handwritten digit recognition by Convolutional Neural Network will be
done using Keras. It is an open-source neural network library that is used to design and
implement deep learning models.

Frontend:
Tkinter (Python) / Web Based (HTML, CSS)

Backend:
Python

Research Questions:
1. Are there commercial engines for offline English handwriting recognition?
2. How to open and read data from a ground truth file in IFN/ENIT dataset?
3. Which line and word segmentation algorithm has better performance on offline
handwritten document images?

References:
[1] Archana N.Vyas, Mukesh m.Goswami, “Classification of Handwritten Gujarati Numerals”,
978-1-4799-8792-4/15/$31.00 ©2015 IEEE
[2] Akanksha Gaur, Sunita Yadav, “Handwritten Hindi character Recognition using K-Means
Clustering and SVM”, 978-1-4799- 5532-9/15/$31.00 ©2015 IEEE
[3] Neha Sahu, Nitin Kali Raman,”An Efficient handwritten Devanagari character Recognition
System Using Neural Network”, 978-1-4673-5090-7/13/$31.00 ©2013 IEEE
[4] Manoj Kumar Mahto, Karamjeet Bhatia, R.K.Sharma, “Combined Horizontal and Vertical
Projection feature Extraction Technique for Gurmukhi Handwritten Character Recognition”,
2015, International conference on Advances in Computer Engineering and Applications
(ICACEA).
[5] Gunjan Singh et al, “Recognition of Handwritten Hindi Characters using Backpropagation
Neural Network” 2012 / (IJCSIT) International Journal of Computer Science and Information
Technologies, Vol. 3 (4) ,4892-4895\

You might also like