Deep Arabic font family and font size recognition

Ibrahim M. Amer, Salma ElSayed, Mostafa G. M. Mostafa

Research output: Contribution to journalArticle

Abstract

Font family and font size recognition became an essential step for document analysis. Font recognition helps to identify the proper segmentation method to be used before feeding the document to the Optical character Recognition (OCR). In this paper, some of the previous techniques used for font family and font size recognition will be discussed then we will discuss the proposed method that is based on deep learning. Two methods have been presented in this paper 1) a method for font family recognition (font size invariant) and 2) a method for font size recognition. Both methods use Deep Convolutional Neural Networks (D-CNN). We evaluated the
proposed method on Arabic Printed Text Image Database (APTI) [7] and on a document generated using APTI database word images and scanned with the scanner.
Original languageEnglish
Number of pages6
JournalInternational Journal of Computer Applications
Volume176
Issue number4
DOIs
Publication statusPublished - 31 Oct 2017

Fingerprint

Optical character recognition
Neural networks
Deep learning

Cite this

Amer, Ibrahim M. ; ElSayed, Salma ; Mostafa, Mostafa G. M. / Deep Arabic font family and font size recognition. In: International Journal of Computer Applications. 2017 ; Vol. 176, No. 4.
@article{e178af6f7b044855bf7bb1f3124c2efe,
title = "Deep Arabic font family and font size recognition",
abstract = "Font family and font size recognition became an essential step for document analysis. Font recognition helps to identify the proper segmentation method to be used before feeding the document to the Optical character Recognition (OCR). In this paper, some of the previous techniques used for font family and font size recognition will be discussed then we will discuss the proposed method that is based on deep learning. Two methods have been presented in this paper 1) a method for font family recognition (font size invariant) and 2) a method for font size recognition. Both methods use Deep Convolutional Neural Networks (D-CNN). We evaluated theproposed method on Arabic Printed Text Image Database (APTI) [7] and on a document generated using APTI database word images and scanned with the scanner.",
author = "Amer, {Ibrahim M.} and Salma ElSayed and Mostafa, {Mostafa G. M.}",
year = "2017",
month = "10",
day = "31",
doi = "10.5120/ijca2017915589",
language = "English",
volume = "176",
journal = "International Journal of Computer Applications",
issn = "0975-8887",
publisher = "Foundation of Computer Science (FCS)",
number = "4",

}

Deep Arabic font family and font size recognition. / Amer, Ibrahim M. ; ElSayed, Salma; Mostafa, Mostafa G. M.

In: International Journal of Computer Applications, Vol. 176, No. 4, 31.10.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deep Arabic font family and font size recognition

AU - Amer, Ibrahim M.

AU - ElSayed, Salma

AU - Mostafa, Mostafa G. M.

PY - 2017/10/31

Y1 - 2017/10/31

N2 - Font family and font size recognition became an essential step for document analysis. Font recognition helps to identify the proper segmentation method to be used before feeding the document to the Optical character Recognition (OCR). In this paper, some of the previous techniques used for font family and font size recognition will be discussed then we will discuss the proposed method that is based on deep learning. Two methods have been presented in this paper 1) a method for font family recognition (font size invariant) and 2) a method for font size recognition. Both methods use Deep Convolutional Neural Networks (D-CNN). We evaluated theproposed method on Arabic Printed Text Image Database (APTI) [7] and on a document generated using APTI database word images and scanned with the scanner.

AB - Font family and font size recognition became an essential step for document analysis. Font recognition helps to identify the proper segmentation method to be used before feeding the document to the Optical character Recognition (OCR). In this paper, some of the previous techniques used for font family and font size recognition will be discussed then we will discuss the proposed method that is based on deep learning. Two methods have been presented in this paper 1) a method for font family recognition (font size invariant) and 2) a method for font size recognition. Both methods use Deep Convolutional Neural Networks (D-CNN). We evaluated theproposed method on Arabic Printed Text Image Database (APTI) [7] and on a document generated using APTI database word images and scanned with the scanner.

U2 - 10.5120/ijca2017915589

DO - 10.5120/ijca2017915589

M3 - Article

VL - 176

JO - International Journal of Computer Applications

JF - International Journal of Computer Applications

SN - 0975-8887

IS - 4

ER -