Using optical character recognition techniques, classification of documents extracted from images

Basit Öğe Kaydı
dc.contributor.authorIbrahim, Abdullahi Abdu
dc.contributor.authorSafaa Salim, Ahmed
dc.contributor.authorAmeer Abd Almaged, Husam
dc.date.accessioned2023-11-07T12:38:36Z
dc.date.available2023-11-07T12:38:36Z
dc.date.issued2023en_US
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractWe now have autonomous cars, speech recognition, efficient online search, and a far greater grasp of the human genome thanks to machine learning techniques developed during the previous ten years. Today, machine learning is employed so often that many times are mistakenly made. It is possible to educate a computer to anticipate outcomes that are challenging for the human brain by trying to teach it certain processes or scenarios. Additionally, these techniques enable us to quickly do various tasks that are frequently impractical or challenging for humans to complete. These factors make machine learning so crucial in today's world. There are two distinct machine learning techniques that were employed in this study. The manuscript materials were moved to the computer and then categorized to address a real-world issue. To complete the procedure, we relied on three fundamental techniques. A scanner or digital camera has converted handwriting or printed materials to digital format. Two alternative optical character recognition (OCR) operations have been used to process these papers. Next, the Naive Bayes method is used to categorize the sentences that were created. The entire project was created using the Windows operating system and Microsoft Visual Studio 12. All components of the study were written in the C# programming language. DLLs and prepared codes were also employed. Exploited.en_US
dc.identifier.citationIbrahim, A. A., Safaa Salim, A., &Ameer Abd Almaged, H. (2023). Using optical character recognition techniques, classification of documents extracted from images. Lecture Notes in Networks and Systems / 4th Doctoral Symposium on Computational Intelligence, 929-941.en_US
dc.identifier.endpage941en_US
dc.identifier.isbn9789819937158
dc.identifier.issn2367-3370
dc.identifier.scopus2-s2.0-85174444201
dc.identifier.scopusqualityN/A
dc.identifier.startpage929en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12939/4225
dc.identifier.volume726en_US
dc.indekslendigikaynakScopus
dc.institutionauthorIbrahim, Abdullahi Abdu
dc.institutionauthorSafaa Salim, Ahmed
dc.institutionauthorAmeer Abd Almaged, Husam
dc.language.isoen
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofLecture Notes in Networks and Systems / 4th Doctoral Symposium on Computational Intelligence
dc.relation.isversionof10.1007/978-981-99-3716-5_74en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectClassificationen_US
dc.subjectImage processingen_US
dc.subjectMachine learningen_US
dc.subjectNaive Bayesen_US
dc.subjectOCRen_US
dc.subjectOptical character recognitionen_US
dc.subjectText miningen_US
dc.titleUsing optical character recognition techniques, classification of documents extracted from images
dc.typeConference Object

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Bilgisayar Mühendisliği Bölümü Koleksiyonu