Implementation of OCR using Convolutional Neural Network (CNN): A Survey
Recently, character recognition and deep learning have caught the attention of many researchers. Optical Character Recognition (OCR) usually takes an image of the character as input and generates the identical character as output. The important role that OCR does is to transform printed materials in...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
College of Education for Pure Sciences
2022-09-01
|
| Series: | مجلة التربية والعلم |
| Subjects: | |
| Online Access: | https://edusj.mosuljournals.com/article_174639_379096db84c3596fe143ba35a2249e2c.pdf |
| _version_ | 1828181448085995520 |
|---|---|
| author | Ahmed Alkaddo Dujan Albaqal |
| author_facet | Ahmed Alkaddo Dujan Albaqal |
| author_sort | Ahmed Alkaddo |
| collection | DOAJ |
| description | Recently, character recognition and deep learning have caught the attention of many researchers. Optical Character Recognition (OCR) usually takes an image of the character as input and generates the identical character as output. The important role that OCR does is to transform printed materials into digital text files. Convolutional Neural Network (CNN) is an influential model that is generous with bright results in optical character recognition (OCR). The state-of-the-art performance which exists in deep neural networks is usually used to handle frequently recognition and classification problems. Many applications are using it, for instance, robotics, traffic monitoring, articles digitization, etc. CNN is designed to adaptively and automatically learn features by using many kinds of layers (convolution layers, pooling layers, and fully connected layers). In this paper we will go through the advantages and recent usage of CNN in OCR and why it’s important to use it in handwritten and printed text recognition and what subjects we can use this technique for. Researchers are progressively using CNN for the machine-printed characters and recognition of handwritten, that is because CNN architectures are suitable for recognition tasks by inputting some images |
| first_indexed | 2024-04-12T06:00:29Z |
| format | Article |
| id | doaj.art-7f9d1f4dc3c340d2a780125cb77e1a10 |
| institution | Directory Open Access Journal |
| issn | 1812-125X 2664-2530 |
| language | Arabic |
| last_indexed | 2024-04-12T06:00:29Z |
| publishDate | 2022-09-01 |
| publisher | College of Education for Pure Sciences |
| record_format | Article |
| series | مجلة التربية والعلم |
| spelling | doaj.art-7f9d1f4dc3c340d2a780125cb77e1a102022-12-22T03:45:02ZaraCollege of Education for Pure Sciencesمجلة التربية والعلم1812-125X2664-25302022-09-01313274110.33899/edusj.2022.133711.1236174639Implementation of OCR using Convolutional Neural Network (CNN): A SurveyAhmed Alkaddo0Dujan Albaqal1Department of Software Engineering, College of Computer Sciences & Mathematics, University of Mosul, Mosul, IraqSoftwares Department, College of Computer Sciences & Mathematics, University of Mosul, Mosul, IraqRecently, character recognition and deep learning have caught the attention of many researchers. Optical Character Recognition (OCR) usually takes an image of the character as input and generates the identical character as output. The important role that OCR does is to transform printed materials into digital text files. Convolutional Neural Network (CNN) is an influential model that is generous with bright results in optical character recognition (OCR). The state-of-the-art performance which exists in deep neural networks is usually used to handle frequently recognition and classification problems. Many applications are using it, for instance, robotics, traffic monitoring, articles digitization, etc. CNN is designed to adaptively and automatically learn features by using many kinds of layers (convolution layers, pooling layers, and fully connected layers). In this paper we will go through the advantages and recent usage of CNN in OCR and why it’s important to use it in handwritten and printed text recognition and what subjects we can use this technique for. Researchers are progressively using CNN for the machine-printed characters and recognition of handwritten, that is because CNN architectures are suitable for recognition tasks by inputting some imageshttps://edusj.mosuljournals.com/article_174639_379096db84c3596fe143ba35a2249e2c.pdfdeep learning,,,،,؛feature extraction,,,،,؛classification |
| spellingShingle | Ahmed Alkaddo Dujan Albaqal Implementation of OCR using Convolutional Neural Network (CNN): A Survey مجلة التربية والعلم deep learning,, ,،,؛feature extraction,, ,،,؛classification |
| title | Implementation of OCR using Convolutional Neural Network (CNN): A Survey |
| title_full | Implementation of OCR using Convolutional Neural Network (CNN): A Survey |
| title_fullStr | Implementation of OCR using Convolutional Neural Network (CNN): A Survey |
| title_full_unstemmed | Implementation of OCR using Convolutional Neural Network (CNN): A Survey |
| title_short | Implementation of OCR using Convolutional Neural Network (CNN): A Survey |
| title_sort | implementation of ocr using convolutional neural network cnn a survey |
| topic | deep learning,, ,،,؛feature extraction,, ,،,؛classification |
| url | https://edusj.mosuljournals.com/article_174639_379096db84c3596fe143ba35a2249e2c.pdf |
| work_keys_str_mv | AT ahmedalkaddo implementationofocrusingconvolutionalneuralnetworkcnnasurvey AT dujanalbaqal implementationofocrusingconvolutionalneuralnetworkcnnasurvey |