1998
DOI: 10.1007/3-540-64381-8_35
|View full text |Cite
|
Sign up to set email alerts
|

Genericity in graphics recognition algorithms

Abstract: We present the new version of the Graphics Recognition Module developed within the Machine Drawing Understanding System (MDUS) for the graphics recognition contest, to be held during the second IAPR Workshop on Graphics Recognition, Nancy, France, 1997. A generic integrated graphics recognition algorithm is adapted to meet the requirements of the contest: straight and circular, solid and dashed lines, horizontal and vertical text, and filled and hollow arrowheads. We present detailed algorithms for recognizing… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
4
0

Year Published

2000
2000
2020
2020

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 15 publications
0
4
0
Order By: Relevance
“…[15] proposed a hybrid algorithm for the same task. [16] presented a method for the recognition of both text and basic parametrical forms in documents. [17], [18] addressed the recognition of text from drawings.…”
Section: Related Workmentioning
confidence: 99%
“…[15] proposed a hybrid algorithm for the same task. [16] presented a method for the recognition of both text and basic parametrical forms in documents. [17], [18] addressed the recognition of text from drawings.…”
Section: Related Workmentioning
confidence: 99%
“…A number of approaches have been proposed for graphics recognition in digital documents, namely engineering drawings, architectural drawings, etc. (Wenyin, 2004;Ramel & Vincent, 2004;Song, Su, Tai, & Cai, 2002;Wang et al, 2006).…”
Section: Existing Work On Document Understandingmentioning
confidence: 99%
“…Both methods however assume that the text does not touch or overlap with graphics. Wenyin et al [7] recognized horizontal or vertical text. Luo et al [3] detached characters from straight lines.…”
Section: Introductionmentioning
confidence: 99%
“…They used a gazetteer (toponym dictionary) to propose a forecasting hypothesis, which characters are in labels and where is their position in the map, having the information from another map in a different scale. Character and text boxes are used in [7] by Wenyin et al The authors considered only horizontal and vertical text in which a character box is a rectangle with rate sides are no larger than 10 pixels to join character boxes. Thus, they built the text box that can grow horizontally or vertically under a threshold to fit the letters.…”
Section: Introductionmentioning
confidence: 99%