Recognition of handwritten digits using convolutional neural network and linear binary pattern

Prashanth Kambli, Amruthalakshmi, E. Naresh

Research output: Contribution to journalArticlepeer-review

Abstract

Over the past few years there has been a tremendous developments observed in the field of computer technology and artificial intelligence, especially the use of machine learning concepts in Research and Industries. The human effort can be further more reduced in recognition, learning, predicting and many other areas using machine learning and deep learning. Any information which has been handwritten documents consisting of digits in digital form like images, recognizing such digits is a challenging task. The proposed system can recognize any handwritten digits in the document which has been converted into digital format. The proposed model includes Convolutional Neural Network (CNN), a deep learning approach with Linear Binary Pattern (LBP) used for feature extraction. In order to classify more effectively we also have used Support Vector Machine to recognize mere similar digits like 1 and 7, 5 and 6 and many others. The proposed system CNN and LBP is implemented on python language; also the system is tested with different images of handwritten digits taken from MNIST dataset. By using proposed model we could able to achieve 98.74% accuracy in predicting the digits in image format.

Original languageEnglish
Pages (from-to)4368-4372
Number of pages5
JournalInternational Journal of Innovative Technology and Exploring Engineering
Volume9
Issue number1
DOIs
Publication statusPublished - 11-2019

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Civil and Structural Engineering
  • Mechanics of Materials
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Recognition of handwritten digits using convolutional neural network and linear binary pattern'. Together they form a unique fingerprint.

Cite this