Mathematical formula detection in heterogeneous document images

Wei Ta Chu; Fan Liu

doi:10.1109/TAAI.2013.38

Mathematical formula detection in heterogeneous document images

Wei Ta Chu, Fan Liu

Department of Computer Science and Information Engineering

Research output: Contribution to conference › Paper › peer-review

19 Citations (Scopus)

Abstract

This paper 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.

Original language	English
Pages	140-145
Number of pages	6
DOIs	https://doi.org/10.1109/TAAI.2013.38
Publication status	Published - 2013
Event	2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013 - Taipei, Taiwan Duration: 2013 Dec 6 → 2013 Dec 8

Other

Other	2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013
Country/Territory	Taiwan
City	Taipei
Period	13-12-06 → 13-12-08

All Science Journal Classification (ASJC) codes

Artificial Intelligence

Access to Document

10.1109/TAAI.2013.38

Cite this

@conference{13ddac5f286e4b109dcc941c8dfff49b,

title = "Mathematical formula detection in heterogeneous document images",

abstract = "This paper 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.",

author = "Chu, {Wei Ta} and Fan Liu",

year = "2013",

doi = "10.1109/TAAI.2013.38",

language = "English",

pages = "140--145",

note = "2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013 ; Conference date: 06-12-2013 Through 08-12-2013",

}

TY - CONF

T1 - Mathematical formula detection in heterogeneous document images

AU - Chu, Wei Ta

AU - Liu, Fan

PY - 2013

Y1 - 2013

N2 - This paper 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.

AB - This paper 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.

UR - http://www.scopus.com/inward/record.url?scp=84899460005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899460005&partnerID=8YFLogxK

U2 - 10.1109/TAAI.2013.38

DO - 10.1109/TAAI.2013.38

M3 - Paper

AN - SCOPUS:84899460005

SP - 140

EP - 145

T2 - 2013 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2013

Y2 - 6 December 2013 through 8 December 2013

ER -

Mathematical formula detection in heterogeneous document images

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this