Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines

Yao Yi Chiang; Craig A. Knoblock

doi:10.1109/ICPR.2006.368

Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines

Yao Yi Chiang, Craig A. Knoblock

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

13 Scopus citations

Abstract

Raster maps are widely available on the Internet. Valuable information such as street lines and labels, however, are all hidden in the raster format. To utilize the information, it is important to recognize the line and character pixels for further processing. This paper presents a novel algorithm using 2-D Discrete Cosine Transformation (DCT) coefficients and Support Vector Machines (SVM) to classify the pixels of lines and characters on raster maps. The experiment results show that our algorithm achieves 98% precision and 85% recall in classifying the line pixels and 83% precision and 96% recall in classifying the character pixels on a variety of raster map sources.

Original language	English (US)
Title of host publication	Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages	1034-1037
Number of pages	4
DOIs	https://doi.org/10.1109/ICPR.2006.368
State	Published - 2006
Externally published	Yes
Event	18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China Duration: Aug 20 2006 → Aug 24 2006

Publication series

Name	Proceedings - International Conference on Pattern Recognition
Volume	2
ISSN (Print)	1051-4651

Other

Other	18th International Conference on Pattern Recognition, ICPR 2006
Country/Territory	China
City	Hong Kong
Period	8/20/06 → 8/24/06

Publisher link

10.1109/ICPR.2006.368

Find It

Find It at U of M Libraries

Cite this

Chiang, Y. Y., & Knoblock, C. A. (2006). Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006 (pp. 1034-1037). Article 1699384 (Proceedings - International Conference on Pattern Recognition; Vol. 2). https://doi.org/10.1109/ICPR.2006.368

Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines. / Chiang, Yao Yi; Knoblock, Craig A.
Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006. 2006. p. 1034-1037 1699384 (Proceedings - International Conference on Pattern Recognition; Vol. 2).

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

Chiang, YY & Knoblock, CA 2006, Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines. in Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006., 1699384, Proceedings - International Conference on Pattern Recognition, vol. 2, pp. 1034-1037, 18th International Conference on Pattern Recognition, ICPR 2006, Hong Kong, China, 8/20/06. https://doi.org/10.1109/ICPR.2006.368

@inproceedings{2249dc05dab94a8abd84bffc62ab0ed1,

title = "Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines",

abstract = "Raster maps are widely available on the Internet. Valuable information such as street lines and labels, however, are all hidden in the raster format. To utilize the information, it is important to recognize the line and character pixels for further processing. This paper presents a novel algorithm using 2-D Discrete Cosine Transformation (DCT) coefficients and Support Vector Machines (SVM) to classify the pixels of lines and characters on raster maps. The experiment results show that our algorithm achieves 98% precision and 85% recall in classifying the line pixels and 83% precision and 96% recall in classifying the character pixels on a variety of raster map sources.",

author = "Chiang, {Yao Yi} and Knoblock, {Craig A.}",

year = "2006",

doi = "10.1109/ICPR.2006.368",

language = "English (US)",

isbn = "0769525210",

series = "Proceedings - International Conference on Pattern Recognition",

pages = "1034--1037",

booktitle = "Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006",

note = "18th International Conference on Pattern Recognition, ICPR 2006 ; Conference date: 20-08-2006 Through 24-08-2006",

}

TY - GEN

T1 - Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines

AU - Chiang, Yao Yi

AU - Knoblock, Craig A.

PY - 2006

Y1 - 2006

N2 - Raster maps are widely available on the Internet. Valuable information such as street lines and labels, however, are all hidden in the raster format. To utilize the information, it is important to recognize the line and character pixels for further processing. This paper presents a novel algorithm using 2-D Discrete Cosine Transformation (DCT) coefficients and Support Vector Machines (SVM) to classify the pixels of lines and characters on raster maps. The experiment results show that our algorithm achieves 98% precision and 85% recall in classifying the line pixels and 83% precision and 96% recall in classifying the character pixels on a variety of raster map sources.

AB - Raster maps are widely available on the Internet. Valuable information such as street lines and labels, however, are all hidden in the raster format. To utilize the information, it is important to recognize the line and character pixels for further processing. This paper presents a novel algorithm using 2-D Discrete Cosine Transformation (DCT) coefficients and Support Vector Machines (SVM) to classify the pixels of lines and characters on raster maps. The experiment results show that our algorithm achieves 98% precision and 85% recall in classifying the line pixels and 83% precision and 96% recall in classifying the character pixels on a variety of raster map sources.

UR - http://www.scopus.com/inward/record.url?scp=34047234957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34047234957&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.368

DO - 10.1109/ICPR.2006.368

M3 - Conference contribution

AN - SCOPUS:34047234957

SN - 0769525210

SN - 9780769525211

T3 - Proceedings - International Conference on Pattern Recognition

SP - 1034

EP - 1037

BT - Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006

T2 - 18th International Conference on Pattern Recognition, ICPR 2006

Y2 - 20 August 2006 through 24 August 2006

ER -

Classification of line and character pixels on raster maps using discrete cosine transformation coefficients and support vector machines

Abstract

Publication series

Other

Publisher link

Find It

Other files and links

Fingerprint

Cite this