Mathematical Formula Detection in Heterogeneous Document Images

碩士 === 國立中正大學 === 資訊工程研究所 === 102 === This thesis presents mathematical formula detection in heterogeneous document images that may contain figures, tables, text, and math formulas. We adopt the method originally proposed for sign detection in natural images to detect non-homogeneous regions and acc...

Full description

Bibliographic Details
Main Authors: Fan Liu, 劉帆
Other Authors: Wei-Ta Chu
Format: Others
Language:en_US
Published: 2013
Online Access:http://ndltd.ncl.edu.tw/handle/59422837155967118173
id ndltd-TW-102CCU00392013
record_format oai_dc
spelling ndltd-TW-102CCU003920132015-10-13T22:57:40Z http://ndltd.ncl.edu.tw/handle/59422837155967118173 Mathematical Formula Detection in Heterogeneous Document Images 異質性文件影像中的數學方程式偵測 Fan Liu 劉帆 碩士 國立中正大學 資訊工程研究所 102 This thesis presents mathematical formula detection in heterogeneous document images that may contain figures, tables, text, and math formulas. We adopt the method originally proposed for sign detection in natural images to detect non-homogeneous regions and accordingly achieve text line detection and segmentation. Novel features based on centroid fluctuation information of non-homogeneous regions are proposed to more appropriately characterize both displayed formulas and embedded formulas. By comparing the proposed method with previous works, we demonstrate the effectiveness of the proposed features. Wei-Ta Chu 朱威達 2013 學位論文 ; thesis 35 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立中正大學 === 資訊工程研究所 === 102 === This thesis presents mathematical formula detection in heterogeneous document images that may contain figures, tables, text, and math formulas. We adopt the method originally proposed for sign detection in natural images to detect non-homogeneous regions and accordingly achieve text line detection and segmentation. Novel features based on centroid fluctuation information of non-homogeneous regions are proposed to more appropriately characterize both displayed formulas and embedded formulas. By comparing the proposed method with previous works, we demonstrate the effectiveness of the proposed features.
author2 Wei-Ta Chu
author_facet Wei-Ta Chu
Fan Liu
劉帆
author Fan Liu
劉帆
spellingShingle Fan Liu
劉帆
Mathematical Formula Detection in Heterogeneous Document Images
author_sort Fan Liu
title Mathematical Formula Detection in Heterogeneous Document Images
title_short Mathematical Formula Detection in Heterogeneous Document Images
title_full Mathematical Formula Detection in Heterogeneous Document Images
title_fullStr Mathematical Formula Detection in Heterogeneous Document Images
title_full_unstemmed Mathematical Formula Detection in Heterogeneous Document Images
title_sort mathematical formula detection in heterogeneous document images
publishDate 2013
url http://ndltd.ncl.edu.tw/handle/59422837155967118173
work_keys_str_mv AT fanliu mathematicalformuladetectioninheterogeneousdocumentimages
AT liúfān mathematicalformuladetectioninheterogeneousdocumentimages
AT fanliu yìzhìxìngwénjiànyǐngxiàngzhōngdeshùxuéfāngchéngshìzhēncè
AT liúfān yìzhìxìngwénjiànyǐngxiàngzhōngdeshùxuéfāngchéngshìzhēncè
_version_ 1718083968375455744