Optimal palette extraction as part of scanned graphics vectorization

Vinciane Lacroix; Mahamadou Idrissa

Optimal palette extraction as part of scanned graphics vectorization

Vinciane Lacroix, Mahamadou Idrissa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The proposed scanned graphics palette extraction process starts with the extraction of colors of uniform regions, then the colors of local features. In order to enhance the discrimination of unsaturated colors, the image is converted into L^*a^*b^* space and the CMC color difference is used together with the Euclidean distance. After the palette extraction, a regularization process modifies the color of a pixel in order to make it coherent with its neighborhood, thus reducing the number of connected components, hence providing one step further to vectorization. Results are shown on scanned maps and on some scanned graphics.

Original language	English
Title of host publication	5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10
Pages	320-325
Number of pages	6
Publication status	Published - 2010
Event	5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10 - Joensuu, Finland Duration: 14 Jun 2010 → 17 Jun 2010

Publication series

Name	5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10

Conference

Conference	5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10
Country/Territory	Finland
City	Joensuu
Period	14/06/10 → 17/06/10

Cite this

Lacroix, V., & Idrissa, M. (2010). Optimal palette extraction as part of scanned graphics vectorization. In 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10 (pp. 320-325). (5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10).

Lacroix, Vinciane ; Idrissa, Mahamadou. / Optimal palette extraction as part of scanned graphics vectorization. 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10. 2010. pp. 320-325 (5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10).

@inproceedings{ade1bcaa7a3a4964937dd341d2f13f5f,

title = "Optimal palette extraction as part of scanned graphics vectorization",

abstract = "The proposed scanned graphics palette extraction process starts with the extraction of colors of uniform regions, then the colors of local features. In order to enhance the discrimination of unsaturated colors, the image is converted into L*a*b* space and the CMC color difference is used together with the Euclidean distance. After the palette extraction, a regularization process modifies the color of a pixel in order to make it coherent with its neighborhood, thus reducing the number of connected components, hence providing one step further to vectorization. Results are shown on scanned maps and on some scanned graphics.",

author = "Vinciane Lacroix and Mahamadou Idrissa",

year = "2010",

language = "English",

isbn = "9781617388897",

series = "5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10",

pages = "320--325",

booktitle = "5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10",

note = "5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10 ; Conference date: 14-06-2010 Through 17-06-2010",

}

Lacroix, V & Idrissa, M 2010, Optimal palette extraction as part of scanned graphics vectorization. in 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10. 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10, pp. 320-325, 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10, Joensuu, Finland, 14/06/10.

Optimal palette extraction as part of scanned graphics vectorization. / Lacroix, Vinciane; Idrissa, Mahamadou.
5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10. 2010. p. 320-325 (5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimal palette extraction as part of scanned graphics vectorization

AU - Lacroix, Vinciane

AU - Idrissa, Mahamadou

PY - 2010

Y1 - 2010

N2 - The proposed scanned graphics palette extraction process starts with the extraction of colors of uniform regions, then the colors of local features. In order to enhance the discrimination of unsaturated colors, the image is converted into L*a*b* space and the CMC color difference is used together with the Euclidean distance. After the palette extraction, a regularization process modifies the color of a pixel in order to make it coherent with its neighborhood, thus reducing the number of connected components, hence providing one step further to vectorization. Results are shown on scanned maps and on some scanned graphics.

AB - The proposed scanned graphics palette extraction process starts with the extraction of colors of uniform regions, then the colors of local features. In order to enhance the discrimination of unsaturated colors, the image is converted into L*a*b* space and the CMC color difference is used together with the Euclidean distance. After the palette extraction, a regularization process modifies the color of a pixel in order to make it coherent with its neighborhood, thus reducing the number of connected components, hence providing one step further to vectorization. Results are shown on scanned maps and on some scanned graphics.

UR - http://www.scopus.com/inward/record.url?scp=78649339550&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78649339550

SN - 9781617388897

T3 - 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10

SP - 320

EP - 325

BT - 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10

T2 - 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10

Y2 - 14 June 2010 through 17 June 2010

ER -

Lacroix V, Idrissa M. Optimal palette extraction as part of scanned graphics vectorization. In 5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10. 2010. p. 320-325. (5th European Conference on Colour in Graphics, Imaging, and Vision and 12th International Symposium on Multispectral Colour Science 2010, CGIV 2010/MCS'10).

Optimal palette extraction as part of scanned graphics vectorization

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this