The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Pengecaman mesin bagi ungkapan matematik pada dokumen bercetak bukanlah perkara remeh walaupun semua aksara dan simbol individu dalam ungkapan boleh dikenali dengan betul. Dalam kertas ini, kaedah pengelasan automatik hubungan ruang antara simbol bersebelahan dalam pasangan dibentangkan. Pengelasan ini penting untuk merealisasikan modul analisis struktur OCR matematik yang tepat. Keputusan eksperimen pada pangkalan data yang sangat besar menunjukkan bahawa pengelasan ini berfungsi dengan baik dengan ketepatan 99.525% dengan menggunakan peta pengedaran yang ditakrifkan oleh dua ciri geometri, saiz relatif dan kedudukan relatif, dengan rawatan yang teliti terhadap ciri-ciri bergantung kepada dokumen.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Walaa ALY, Seiichi UCHIDA, Masakazu SUZUKI, "Automatic Classification of Spatial Relationships among Mathematical Symbols Using Geometric Features" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 11, pp. 2235-2243, November 2009, doi: 10.1587/transinf.E92.D.2235.
Abstract: Machine recognition of mathematical expressions on printed documents is not trivial even when all the individual characters and symbols in an expression can be recognized correctly. In this paper, an automatic classification method of spatial relationships between the adjacent symbols in a pair is presented. This classification is important to realize an accurate structure analysis module of math OCR. Experimental results on very large databases showed that this classification worked well with an accuracy of 99.525% by using distribution maps which are defined by two geometric features, relative size and relative position, with careful treatment on document-dependent characteristics.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2235/_p
Salinan
@ARTICLE{e92-d_11_2235,
author={Walaa ALY, Seiichi UCHIDA, Masakazu SUZUKI, },
journal={IEICE TRANSACTIONS on Information},
title={Automatic Classification of Spatial Relationships among Mathematical Symbols Using Geometric Features},
year={2009},
volume={E92-D},
number={11},
pages={2235-2243},
abstract={Machine recognition of mathematical expressions on printed documents is not trivial even when all the individual characters and symbols in an expression can be recognized correctly. In this paper, an automatic classification method of spatial relationships between the adjacent symbols in a pair is presented. This classification is important to realize an accurate structure analysis module of math OCR. Experimental results on very large databases showed that this classification worked well with an accuracy of 99.525% by using distribution maps which are defined by two geometric features, relative size and relative position, with careful treatment on document-dependent characteristics.},
keywords={},
doi={10.1587/transinf.E92.D.2235},
ISSN={1745-1361},
month={November},}
Salinan
TY - JOUR
TI - Automatic Classification of Spatial Relationships among Mathematical Symbols Using Geometric Features
T2 - IEICE TRANSACTIONS on Information
SP - 2235
EP - 2243
AU - Walaa ALY
AU - Seiichi UCHIDA
AU - Masakazu SUZUKI
PY - 2009
DO - 10.1587/transinf.E92.D.2235
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2009
AB - Machine recognition of mathematical expressions on printed documents is not trivial even when all the individual characters and symbols in an expression can be recognized correctly. In this paper, an automatic classification method of spatial relationships between the adjacent symbols in a pair is presented. This classification is important to realize an accurate structure analysis module of math OCR. Experimental results on very large databases showed that this classification worked well with an accuracy of 99.525% by using distribution maps which are defined by two geometric features, relative size and relative position, with careful treatment on document-dependent characteristics.
ER -