Classification of heterogeneous Malayalam documents based on structural features using deep learning models
The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manuall...
Gespeichert in:
| Veröffentlicht in: | International journal of electrical and computer engineering (Malacca, Malacca) Malacca), 2023-02, Vol.13 (1), p.894 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | 894 |
| container_title | International journal of electrical and computer engineering (Malacca, Malacca) |
| container_volume | 13 |
| creator | Balakrishnan Jayakumari, Bipin Nair Thomas Kavana, Amel |
| description | The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manually collected from different sources. The method of research proceeds with preprocessing, feature extraction, and classification. The proposed work deals with three fine-tuned deep learning models such as visual geometry group-16 (VGG-16), convolutional neural network (CNN) and AlexNet. The models attained high accuracies of 99.7%, 96%, and 95%, respectively. Among the three models, the fine-tuned VGG-16 model was found to perform better attaining a very high accuracy on the dataset. As a future work, methods to classify the documents based on content as well as spectral features can be developed. |
| doi_str_mv | 10.11591/ijece.v13i1.pp894-901 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2766677012</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2766677012</sourcerecordid><originalsourceid>FETCH-LOGICAL-c145t-f6f40d1aab82438db4cf977caa55c47acad91b99e86abda04e14efb6ea2c7cae3</originalsourceid><addsrcrecordid>eNotkE1LxDAQhosouKz7FyTguWvSpkl6lMUvWPGi5zBNJmvXtqlJK-y_N1YPw7wzPMzAk2XXjG4Zq2p22x7R4PablS3bjqOqeV5TdpatClkUeVFJdZ4yVSpXkqrLbBNj21DOJadSVKvsc9dBWrnWwNT6gXhHPnDC4A84oJ8jeYEOTql6Yr2ZexymSBqIaEmi4xRmM80BOuIQUsBI5tgOB2IRR9IhhOF36r3FLl5lFw66iJv_vs7eH-7fdk_5_vXxeXe3zw3j1ZQ74Ti1DKBRBS-VbbhxtZQGoKoMl2DA1qypa1QCGguUI-PoGoFQmERhuc5u_u6OwX_NGCd99HMY0ktdSCGElJQViRJ_lAk-xoBOj6HtIZw0o3pxqxe3enGrF7c6uS1_ACnUdA8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2766677012</pqid></control><display><type>article</type><title>Classification of heterogeneous Malayalam documents based on structural features using deep learning models</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Balakrishnan Jayakumari, Bipin Nair ; Thomas Kavana, Amel</creator><creatorcontrib>Balakrishnan Jayakumari, Bipin Nair ; Thomas Kavana, Amel</creatorcontrib><description>The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manually collected from different sources. The method of research proceeds with preprocessing, feature extraction, and classification. The proposed work deals with three fine-tuned deep learning models such as visual geometry group-16 (VGG-16), convolutional neural network (CNN) and AlexNet. The models attained high accuracies of 99.7%, 96%, and 95%, respectively. Among the three models, the fine-tuned VGG-16 model was found to perform better attaining a very high accuracy on the dataset. As a future work, methods to classify the documents based on content as well as spectral features can be developed.</description><identifier>ISSN: 2088-8708</identifier><identifier>EISSN: 2722-2578</identifier><identifier>EISSN: 2088-8708</identifier><identifier>DOI: 10.11591/ijece.v13i1.pp894-901</identifier><language>eng</language><publisher>Yogyakarta: IAES Institute of Advanced Engineering and Science</publisher><subject>Accuracy ; Agreements ; Artificial neural networks ; Classification ; Comparative studies ; Computer science ; Coronaviruses ; COVID-19 ; Datasets ; Deep learning ; Digitization ; Documents ; Feature extraction ; Machine learning ; Methods ; Neural networks ; Tobacco</subject><ispartof>International journal of electrical and computer engineering (Malacca, Malacca), 2023-02, Vol.13 (1), p.894</ispartof><rights>Copyright IAES Institute of Advanced Engineering and Science 2023</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0003-4592-4947 ; 0000-0003-0220-0527</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Balakrishnan Jayakumari, Bipin Nair</creatorcontrib><creatorcontrib>Thomas Kavana, Amel</creatorcontrib><title>Classification of heterogeneous Malayalam documents based on structural features using deep learning models</title><title>International journal of electrical and computer engineering (Malacca, Malacca)</title><description>The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manually collected from different sources. The method of research proceeds with preprocessing, feature extraction, and classification. The proposed work deals with three fine-tuned deep learning models such as visual geometry group-16 (VGG-16), convolutional neural network (CNN) and AlexNet. The models attained high accuracies of 99.7%, 96%, and 95%, respectively. Among the three models, the fine-tuned VGG-16 model was found to perform better attaining a very high accuracy on the dataset. As a future work, methods to classify the documents based on content as well as spectral features can be developed.</description><subject>Accuracy</subject><subject>Agreements</subject><subject>Artificial neural networks</subject><subject>Classification</subject><subject>Comparative studies</subject><subject>Computer science</subject><subject>Coronaviruses</subject><subject>COVID-19</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Digitization</subject><subject>Documents</subject><subject>Feature extraction</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Tobacco</subject><issn>2088-8708</issn><issn>2722-2578</issn><issn>2088-8708</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNotkE1LxDAQhosouKz7FyTguWvSpkl6lMUvWPGi5zBNJmvXtqlJK-y_N1YPw7wzPMzAk2XXjG4Zq2p22x7R4PablS3bjqOqeV5TdpatClkUeVFJdZ4yVSpXkqrLbBNj21DOJadSVKvsc9dBWrnWwNT6gXhHPnDC4A84oJ8jeYEOTql6Yr2ZexymSBqIaEmi4xRmM80BOuIQUsBI5tgOB2IRR9IhhOF36r3FLl5lFw66iJv_vs7eH-7fdk_5_vXxeXe3zw3j1ZQ74Ti1DKBRBS-VbbhxtZQGoKoMl2DA1qypa1QCGguUI-PoGoFQmERhuc5u_u6OwX_NGCd99HMY0ktdSCGElJQViRJ_lAk-xoBOj6HtIZw0o3pxqxe3enGrF7c6uS1_ACnUdA8</recordid><startdate>20230201</startdate><enddate>20230201</enddate><creator>Balakrishnan Jayakumari, Bipin Nair</creator><creator>Thomas Kavana, Amel</creator><general>IAES Institute of Advanced Engineering and Science</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BVBZV</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L6V</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><orcidid>https://orcid.org/0000-0003-4592-4947</orcidid><orcidid>https://orcid.org/0000-0003-0220-0527</orcidid></search><sort><creationdate>20230201</creationdate><title>Classification of heterogeneous Malayalam documents based on structural features using deep learning models</title><author>Balakrishnan Jayakumari, Bipin Nair ; Thomas Kavana, Amel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c145t-f6f40d1aab82438db4cf977caa55c47acad91b99e86abda04e14efb6ea2c7cae3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Agreements</topic><topic>Artificial neural networks</topic><topic>Classification</topic><topic>Comparative studies</topic><topic>Computer science</topic><topic>Coronaviruses</topic><topic>COVID-19</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Digitization</topic><topic>Documents</topic><topic>Feature extraction</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Tobacco</topic><toplevel>online_resources</toplevel><creatorcontrib>Balakrishnan Jayakumari, Bipin Nair</creatorcontrib><creatorcontrib>Thomas Kavana, Amel</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>East & South Asia Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>International journal of electrical and computer engineering (Malacca, Malacca)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Balakrishnan Jayakumari, Bipin Nair</au><au>Thomas Kavana, Amel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classification of heterogeneous Malayalam documents based on structural features using deep learning models</atitle><jtitle>International journal of electrical and computer engineering (Malacca, Malacca)</jtitle><date>2023-02-01</date><risdate>2023</risdate><volume>13</volume><issue>1</issue><spage>894</spage><pages>894-</pages><issn>2088-8708</issn><eissn>2722-2578</eissn><eissn>2088-8708</eissn><abstract>The proposed work gives a comparative study on performance of various pretrained deep learning models for classifying Malayalam documents such as agreement documents, notebook images, and palm leaves. The documents are classified based on their visual and structural features. The dataset was manually collected from different sources. The method of research proceeds with preprocessing, feature extraction, and classification. The proposed work deals with three fine-tuned deep learning models such as visual geometry group-16 (VGG-16), convolutional neural network (CNN) and AlexNet. The models attained high accuracies of 99.7%, 96%, and 95%, respectively. Among the three models, the fine-tuned VGG-16 model was found to perform better attaining a very high accuracy on the dataset. As a future work, methods to classify the documents based on content as well as spectral features can be developed.</abstract><cop>Yogyakarta</cop><pub>IAES Institute of Advanced Engineering and Science</pub><doi>10.11591/ijece.v13i1.pp894-901</doi><orcidid>https://orcid.org/0000-0003-4592-4947</orcidid><orcidid>https://orcid.org/0000-0003-0220-0527</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2088-8708 |
| ispartof | International journal of electrical and computer engineering (Malacca, Malacca), 2023-02, Vol.13 (1), p.894 |
| issn | 2088-8708 2722-2578 2088-8708 |
| language | eng |
| recordid | cdi_proquest_journals_2766677012 |
| source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Accuracy Agreements Artificial neural networks Classification Comparative studies Computer science Coronaviruses COVID-19 Datasets Deep learning Digitization Documents Feature extraction Machine learning Methods Neural networks Tobacco |
| title | Classification of heterogeneous Malayalam documents based on structural features using deep learning models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T03%3A39%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Classification%20of%20heterogeneous%20Malayalam%20documents%20based%20on%20structural%20features%20using%20deep%20learning%20models&rft.jtitle=International%20journal%20of%20electrical%20and%20computer%20engineering%20(Malacca,%20Malacca)&rft.au=Balakrishnan%20Jayakumari,%20Bipin%20Nair&rft.date=2023-02-01&rft.volume=13&rft.issue=1&rft.spage=894&rft.pages=894-&rft.issn=2088-8708&rft.eissn=2722-2578&rft_id=info:doi/10.11591/ijece.v13i1.pp894-901&rft_dat=%3Cproquest_cross%3E2766677012%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2766677012&rft_id=info:pmid/&rfr_iscdi=true |