Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network
In this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/4383037 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561505622556672 |
|---|---|
| author | Mujtaba Husnain Malik Muhammad Saad Missen Shahzad Mumtaz Dost Muhammad Khan Mickäel Coustaty Muhammad Muzzamil Luqman Jean-Marc Ogier Hizbullah Khattak Sikandar Ali Ali Samad |
| author_facet | Mujtaba Husnain Malik Muhammad Saad Missen Shahzad Mumtaz Dost Muhammad Khan Mickäel Coustaty Muhammad Muzzamil Luqman Jean-Marc Ogier Hizbullah Khattak Sikandar Ali Ali Samad |
| author_sort | Mujtaba Husnain |
| collection | DOAJ |
| description | In this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on the shape similarity. We performed three tasks in a disciplined order; namely, (i) we generated a state-of-the-art dataset of both the Urdu handwritten characters and numerals by inviting a number of native Urdu participants from different social and academic groups, since there is no publicly available dataset of such type till date, then (ii) applied classical approaches of dimensionality reduction and data visualization like Principal Component Analysis (PCA), Autoencoders (AE) in comparison with t-Stochastic Neighborhood Embedding (t-SNE), and (iii) used the reduced dimensions obtained through PCA, AE, and t-SNE for recognition of Urdu handwritten characters and numerals using a deep network like Convolution Neural Network (CNN). The accuracy achieved in recognition of Urdu characters and numerals among the approaches for the same task is found to be much better. The novelty lies in the fact that the resulting reduced dimensions are used for the first time for the recognition of Urdu handwritten text at the character level instead of using the whole multidimensional data. This results in consuming less computation time with the same accuracy when compared with processing time consumed by recognition approaches applied to other datasets for the same task using the whole data. |
| format | Article |
| id | doaj-art-79392714b2574f2f992636cadc10199a |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-79392714b2574f2f992636cadc10199a2025-02-03T01:24:47ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/43830374383037Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep NetworkMujtaba Husnain0Malik Muhammad Saad Missen1Shahzad Mumtaz2Dost Muhammad Khan3Mickäel Coustaty4Muhammad Muzzamil Luqman5Jean-Marc Ogier6Hizbullah Khattak7Sikandar Ali8Ali Samad9Department of Information Technology, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur 63100, PakistanDepartment of Information Technology, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur 63100, PakistanDepartment of Information Technology, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur 63100, PakistanDepartment of Information Technology, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur 63100, PakistanL3i Lab, Université of La Rochelle Av. Michel Crépeau, 17000 La Rochelle, FranceL3i Lab, Université of La Rochelle Av. Michel Crépeau, 17000 La Rochelle, FranceL3i Lab, Université of La Rochelle Av. Michel Crépeau, 17000 La Rochelle, FranceDepartment of Information Technology, Hazara University Mansehra, 21120 Khyber Pakhtunkhwa, PakistanDepartment of Information Technology, The University of Haripur, Khyber Pakhtunkhwa, PakistanDepartment of Information Technology, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur 63100, PakistanIn this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on the shape similarity. We performed three tasks in a disciplined order; namely, (i) we generated a state-of-the-art dataset of both the Urdu handwritten characters and numerals by inviting a number of native Urdu participants from different social and academic groups, since there is no publicly available dataset of such type till date, then (ii) applied classical approaches of dimensionality reduction and data visualization like Principal Component Analysis (PCA), Autoencoders (AE) in comparison with t-Stochastic Neighborhood Embedding (t-SNE), and (iii) used the reduced dimensions obtained through PCA, AE, and t-SNE for recognition of Urdu handwritten characters and numerals using a deep network like Convolution Neural Network (CNN). The accuracy achieved in recognition of Urdu characters and numerals among the approaches for the same task is found to be much better. The novelty lies in the fact that the resulting reduced dimensions are used for the first time for the recognition of Urdu handwritten text at the character level instead of using the whole multidimensional data. This results in consuming less computation time with the same accuracy when compared with processing time consumed by recognition approaches applied to other datasets for the same task using the whole data.http://dx.doi.org/10.1155/2021/4383037 |
| spellingShingle | Mujtaba Husnain Malik Muhammad Saad Missen Shahzad Mumtaz Dost Muhammad Khan Mickäel Coustaty Muhammad Muzzamil Luqman Jean-Marc Ogier Hizbullah Khattak Sikandar Ali Ali Samad Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network Complexity |
| title | Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network |
| title_full | Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network |
| title_fullStr | Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network |
| title_full_unstemmed | Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network |
| title_short | Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network |
| title_sort | urdu handwritten characters data visualization and recognition using distributed stochastic neighborhood embedding and deep network |
| url | http://dx.doi.org/10.1155/2021/4383037 |
| work_keys_str_mv | AT mujtabahusnain urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT malikmuhammadsaadmissen urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT shahzadmumtaz urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT dostmuhammadkhan urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT mickaelcoustaty urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT muhammadmuzzamilluqman urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT jeanmarcogier urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT hizbullahkhattak urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT sikandarali urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork AT alisamad urduhandwrittencharactersdatavisualizationandrecognitionusingdistributedstochasticneighborhoodembeddinganddeepnetwork |