Scribd
Upload
144 views

Hand Written Digit Recognition Using Artificial Neural Network

The document discusses handwritten digit recognition using an artificial neural network. It presents the work done by a group of students under the guidance of their professor. The document includes an abstract, information about the MNIST dataset, and descriptions of the system architecture, data flow diagram, and sequence diagram for a handwritten digit recognition system based on neural networks.

Uploaded by

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

Hand Written Digit Recognition Using Artificial Neural Network

The document discusses handwritten digit recognition using an artificial neural network. It presents the work done by a group of students under the guidance of their professor. The document includes an abstract, information about the MNIST dataset, and descriptions of the system architecture, data flow diagram, and sequence diagram for a handwritten digit recognition system based on neural networks.

Uploaded by

Ravi Shankar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

HAND WRITTEN DIGIT

RECOGNITION USING
Artificial neural network

Under the Guidance of : Presented By :


Mrs. Farhana Kausar
Assistant Professor Sanjeeva Kumar(1AT17CS072)
Seenakula Ravi Shankar(1AT17CS077)
Shashank MV(1AT17CS078)
Vandana KC(1AT17CS092)
TABLE OF CONTENTS

• Abstract • MNIST Dataset • Architecture of the system

• Data Flow Diagram • Sequence Diagram • Class Diagram


Abstract

 The handwritten digit recognition is the ability of computers to recognize human handwritten digits.
 It is a hard task for the machine because handwritten digits are not perfect and can be made with many
different flavors.
 The handwritten digit recognition is the solution to this problem which uses the image of a digit and
recognizes the digit present in the image.
MNIST dataset

 MNIST dataset is widely used dataset in machine


learning for handwritten recognition, image
classification and many more.
 The MNIST dataset is short form for the
modified national institute of standards and
technology dataset.
 It is a dataset of 60,000 small square 28×28 pixel
grayscale images of handwritten single digits
between 0 and 9.
Architecture of the system
  At The role of the pre-processing step it perform various tasks on
the input images. The fundamental motivation behind pre-
processing is to take off a fascinating example from the
background.
 Pre-processed digit images are segmented into a sub-image of
individual digits, which are assigned a number to each digits.
 In the feature extraction stage redundancy from the data is
removed.
 In the Training and Recognition step the extracted feature vectors
are taken as an individual input to each of the following classifiers.
In order to showcase the working system model extracted features
are combined and defined using following three classifiers: K-
Nearest Neighbor, Random Forest Classifier, Support Vector
Machine.
Data flow diagram

   Preprocessing stage has several tasks to be done:


Binarization, Noise filtering, Smoothing, Normalization.

 Segmentation : An image of the sequence of character is


decomposed int sub-images of individual character.
 Feature Extraction : Feature Extraction Based on Character
Geometry, It extracts different line types that form a particular
character.
 The feature extraction technique explained was tested using
Neural Network which was trained with the feature vectors
obtained from the system proposed.
 Classification and Recognition, Design for the Artificial Neural
Network.
Sequence diagram
 This is the sequence diagram of the system model. The diagram
describes the sequence of steps to be taken while performing
execution.
 The ANN model works in the following sequence.
 User uploads a particular image of any digit which he wants to
recognize.
 The image will be processed by the system. On running the system
code the output is generated that shows which is the digit uploaded by
the user and also displays the accuracy rate predicted by the model.
 On uploading image with different resolutions other than the one
mentioned in the code, the output generated shows error, and displays
an error message to the user.
Usecase diagram
THANK
YOU

You might also like