Investigating the Various Approaches towards Handwritten Digit Recognition
| Main Authors: | Prashanth Kambli, Amruthalakshmi |
|---|---|
| Format: | Article Journal |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/3365747 |
| ctrlnum |
3365747 |
|---|---|
| fullrecord |
<?xml version="1.0"?>
<dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"><creator>Prashanth Kambli</creator><creator>Amruthalakshmi</creator><date>2019-08-12</date><description>Pattern recognition plays a vital role due to demand in artificial intelligence in practical problem. One of the problem is, that the machine faced problem in handwritten digit recognition. To recognize the digits, different features are considered such as style, orientation, curve, size, edge, thickness of the digit. Based on these factors they classifies the digits. This paper describes the different approaches that where followed to recognize the Handwritten digits. And the discussion about the different algorithms used. There are two steps involved, one is feature extraction for that there are many feature extraction methods available like, Linear Binary Pattern, Histogram Oriented Graph, Convolutional Neural Network and many more algorithms. Another one is feature classification for that many machine learning methods available like Support Vector Machine, K Nearest Neighbor so on. The main objective of all these approaches is to improve the prediction accuracy. So our main intention is to find the most appropriate method which could give highest prediction rate. In order to obtain that we created a comparative table, which compares with respect to classification method, feature extraction method, accuracy, purpose, pros and cons. Also plotted graph to compare them.
</description><identifier>https://zenodo.org/record/3365747</identifier><identifier>10.5281/zenodo.3365747</identifier><identifier>oai:zenodo.org:3365747</identifier><language>eng</language><relation>doi:10.5281/zenodo.3365746</relation><relation>url:https://zenodo.org/communities/mat-journals</relation><rights>info:eu-repo/semantics/openAccess</rights><rights>https://creativecommons.org/licenses/by/4.0/legalcode</rights><source>Journal of Network Security Computer Networks 5(3) 1-7</source><subject>Artificial Neural Network, Convolutional Neural Network, Artificial Neural Network, Histogram Oriented Gradient, Linear Binary Pattern Variant, K- Nearest Neighbour, Support Vector Machine</subject><subject>Computer Science / IT Journals</subject><title>Investigating the Various Approaches towards Handwritten Digit Recognition</title><type>Journal:Article</type><type>Journal:Article</type><recordID>3365747</recordID></dc>
|
| language |
eng |
| format |
Journal:Article Journal Journal:Journal |
| author |
Prashanth Kambli Amruthalakshmi |
| title |
Investigating the Various Approaches towards Handwritten Digit Recognition |
| publishDate |
2019 |
| topic |
Artificial Neural Network Convolutional Neural Network Histogram Oriented Gradient Linear Binary Pattern Variant K- Nearest Neighbour Support Vector Machine Computer Science IT Journals |
| url |
https://zenodo.org/record/3365747 |
| contents |
Pattern recognition plays a vital role due to demand in artificial intelligence in practical problem. One of the problem is, that the machine faced problem in handwritten digit recognition. To recognize the digits, different features are considered such as style, orientation, curve, size, edge, thickness of the digit. Based on these factors they classifies the digits. This paper describes the different approaches that where followed to recognize the Handwritten digits. And the discussion about the different algorithms used. There are two steps involved, one is feature extraction for that there are many feature extraction methods available like, Linear Binary Pattern, Histogram Oriented Graph, Convolutional Neural Network and many more algorithms. Another one is feature classification for that many machine learning methods available like Support Vector Machine, K Nearest Neighbor so on. The main objective of all these approaches is to improve the prediction accuracy. So our main intention is to find the most appropriate method which could give highest prediction rate. In order to obtain that we created a comparative table, which compares with respect to classification method, feature extraction method, accuracy, purpose, pros and cons. Also plotted graph to compare them.
|
| id |
IOS16997.3365747 |
| institution |
ZAIN Publications |
| institution_id |
7213 |
| institution_type |
library:special library |
| library |
Cognizance Journal of Multidisciplinary Studies |
| library_id |
5267 |
| collection |
Cognizance Journal of Multidisciplinary Studies |
| repository_id |
16997 |
| subject_area |
Multidisciplinary |
| city |
Stockholm |
| province |
INTERNASIONAL |
| shared_to_ipusnas_str |
1 |
| repoId |
IOS16997 |
| first_indexed |
2022-06-06T05:17:46Z |
| last_indexed |
2022-06-06T05:17:46Z |
| recordtype |
dc |
| _version_ |
1734904816926195712 |
| score |
17.610285 |