An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition
Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to e...
Gespeichert in:
| Veröffentlicht in: | Automatic control and computer sciences 2023-06, Vol.57 (3), p.267-275 |
|---|---|
| 1. Verfasser: | |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 275 |
|---|---|
| container_issue | 3 |
| container_start_page | 267 |
| container_title | Automatic control and computer sciences |
| container_volume | 57 |
| creator | Mamouni El Mamoun |
| description | Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to extract features from character images. Then, a support vector machine (SVM) was used for classification. By combining CNN and SVM, the aim is to exploit both technologies’ strengths. Four hybrid models are proposed in this work. Several databases such as HACDB, HIJJA, AHCD, and MNIST were used to evaluate them. The results obtained are satisfactory compared to similar studies in the literature, with a test accuracy of 89.7, 88.8, 97.3, and 99.4%, respectively. |
| doi_str_mv | 10.3103/S0146411623030069 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2832825821</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2832825821</sourcerecordid><originalsourceid>FETCH-LOGICAL-c316t-e15a39408e7d310391feae1a134eba4a253c3bef3589421a1805da73ea73b7f53</originalsourceid><addsrcrecordid>eNp1kEFLAzEQhYMoWKs_wFvA82qy2Wyzx1LUClXBqnhbsttJTd0ma5Jt8eg_N2sFD-IhDDPvfW-YIHRKyTmjhF3MCc3yjNI8ZYQRkhd7aEA5Fwkl4mUfDXo56fVDdOT9ipCoiXyAPscGXyoFddAbwBO7rrSRQVuDrYqt2dim61vZ4Dvo3HcJW-vesDQLPO_a1rqAnyNvHb6V9as2MaaR3mulwWEVx2MnK13jaSS2TocABj9AbZdG98nH6EDJxsPJTx2ip6vLx8k0md1f30zGs6RmNA8JUC5ZkREBo0V_cUEVSKCSsgwqmcmUs5pVoBgXRZbGuSB8IUcM4qtGirMhOtvlts6-d-BDubKdi4f5MhUsFSkXKY0uunPVznrvQJWt02vpPkpKyn5v-eenI5PuGB-9ZgnuN_l_6AshI4E9</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2832825821</pqid></control><display><type>article</type><title>An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition</title><source>Springer Nature - Complete Springer Journals</source><creator>Mamouni El Mamoun</creator><creatorcontrib>Mamouni El Mamoun</creatorcontrib><description>Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to extract features from character images. Then, a support vector machine (SVM) was used for classification. By combining CNN and SVM, the aim is to exploit both technologies’ strengths. Four hybrid models are proposed in this work. Several databases such as HACDB, HIJJA, AHCD, and MNIST were used to evaluate them. The results obtained are satisfactory compared to similar studies in the literature, with a test accuracy of 89.7, 88.8, 97.3, and 99.4%, respectively.</description><identifier>ISSN: 0146-4116</identifier><identifier>EISSN: 1558-108X</identifier><identifier>DOI: 10.3103/S0146411623030069</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Artificial neural networks ; Character recognition ; Classification ; Computer Science ; Control Structures and Microprogramming ; Handwriting recognition ; Support vector machines</subject><ispartof>Automatic control and computer sciences, 2023-06, Vol.57 (3), p.267-275</ispartof><rights>Allerton Press, Inc. 2023. ISSN 0146-4116, Automatic Control and Computer Sciences, 2023, Vol. 57, No. 3, pp. 267–275. © Allerton Press, Inc., 2023.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c316t-e15a39408e7d310391feae1a134eba4a253c3bef3589421a1805da73ea73b7f53</citedby><cites>FETCH-LOGICAL-c316t-e15a39408e7d310391feae1a134eba4a253c3bef3589421a1805da73ea73b7f53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.3103/S0146411623030069$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.3103/S0146411623030069$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,777,781,27905,27906,41469,42538,51300</link.rule.ids></links><search><creatorcontrib>Mamouni El Mamoun</creatorcontrib><title>An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition</title><title>Automatic control and computer sciences</title><addtitle>Aut. Control Comp. Sci</addtitle><description>Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to extract features from character images. Then, a support vector machine (SVM) was used for classification. By combining CNN and SVM, the aim is to exploit both technologies’ strengths. Four hybrid models are proposed in this work. Several databases such as HACDB, HIJJA, AHCD, and MNIST were used to evaluate them. The results obtained are satisfactory compared to similar studies in the literature, with a test accuracy of 89.7, 88.8, 97.3, and 99.4%, respectively.</description><subject>Artificial neural networks</subject><subject>Character recognition</subject><subject>Classification</subject><subject>Computer Science</subject><subject>Control Structures and Microprogramming</subject><subject>Handwriting recognition</subject><subject>Support vector machines</subject><issn>0146-4116</issn><issn>1558-108X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp1kEFLAzEQhYMoWKs_wFvA82qy2Wyzx1LUClXBqnhbsttJTd0ma5Jt8eg_N2sFD-IhDDPvfW-YIHRKyTmjhF3MCc3yjNI8ZYQRkhd7aEA5Fwkl4mUfDXo56fVDdOT9ipCoiXyAPscGXyoFddAbwBO7rrSRQVuDrYqt2dim61vZ4Dvo3HcJW-vesDQLPO_a1rqAnyNvHb6V9as2MaaR3mulwWEVx2MnK13jaSS2TocABj9AbZdG98nH6EDJxsPJTx2ip6vLx8k0md1f30zGs6RmNA8JUC5ZkREBo0V_cUEVSKCSsgwqmcmUs5pVoBgXRZbGuSB8IUcM4qtGirMhOtvlts6-d-BDubKdi4f5MhUsFSkXKY0uunPVznrvQJWt02vpPkpKyn5v-eenI5PuGB-9ZgnuN_l_6AshI4E9</recordid><startdate>20230601</startdate><enddate>20230601</enddate><creator>Mamouni El Mamoun</creator><general>Pleiades Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20230601</creationdate><title>An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition</title><author>Mamouni El Mamoun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c316t-e15a39408e7d310391feae1a134eba4a253c3bef3589421a1805da73ea73b7f53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Character recognition</topic><topic>Classification</topic><topic>Computer Science</topic><topic>Control Structures and Microprogramming</topic><topic>Handwriting recognition</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mamouni El Mamoun</creatorcontrib><collection>CrossRef</collection><jtitle>Automatic control and computer sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mamouni El Mamoun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition</atitle><jtitle>Automatic control and computer sciences</jtitle><stitle>Aut. Control Comp. Sci</stitle><date>2023-06-01</date><risdate>2023</risdate><volume>57</volume><issue>3</issue><spage>267</spage><epage>275</epage><pages>267-275</pages><issn>0146-4116</issn><eissn>1558-108X</eissn><abstract>Recognition of handwritten Arabic characters remains a major challenge for researchers, given the significant differences in handwriting. This paper presents a hybrid method based on combining the most efficient classification techniques. A trained convolutional neural network (CNN) was applied to extract features from character images. Then, a support vector machine (SVM) was used for classification. By combining CNN and SVM, the aim is to exploit both technologies’ strengths. Four hybrid models are proposed in this work. Several databases such as HACDB, HIJJA, AHCD, and MNIST were used to evaluate them. The results obtained are satisfactory compared to similar studies in the literature, with a test accuracy of 89.7, 88.8, 97.3, and 99.4%, respectively.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.3103/S0146411623030069</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0146-4116 |
| ispartof | Automatic control and computer sciences, 2023-06, Vol.57 (3), p.267-275 |
| issn | 0146-4116 1558-108X |
| language | eng |
| recordid | cdi_proquest_journals_2832825821 |
| source | Springer Nature - Complete Springer Journals |
| subjects | Artificial neural networks Character recognition Classification Computer Science Control Structures and Microprogramming Handwriting recognition Support vector machines |
| title | An Effective Combination of Convolutional Neural Network and Support Vector Machine Classifier for Arabic Handwritten Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T01%3A52%3A12IST&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=An%20Effective%20Combination%20of%20Convolutional%20Neural%20Network%20and%20Support%20Vector%20Machine%20Classifier%20for%20Arabic%20Handwritten%20Recognition&rft.jtitle=Automatic%20control%20and%20computer%20sciences&rft.au=Mamouni%20El%20Mamoun&rft.date=2023-06-01&rft.volume=57&rft.issue=3&rft.spage=267&rft.epage=275&rft.pages=267-275&rft.issn=0146-4116&rft.eissn=1558-108X&rft_id=info:doi/10.3103/S0146411623030069&rft_dat=%3Cproquest_cross%3E2832825821%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=2832825821&rft_id=info:pmid/&rfr_iscdi=true |