The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects

Andrew P. Paplinski

doi:10.1007/978-3-642-39065-4_63

The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects

Andrew P. Paplinski

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

Abstract

The recently introduced angular integral of the Radon transform (aniRT) seems to be a good candidate as a feature vector used in categorization of visual objects in a rotation invariant fashion. We investigate application of aniRT in situations when the number of objects is significant, for example, Chinese characters. Typically, the aniRT feature vector spans the diagonal of the visual object. We show that a subset of the full aniRT vector delivers a good categorization results in a timely manner.

Original language	English
Title of host publication	Advances in Neural Networks (ISNN 2013)
Subtitle of host publication	10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I
Editors	Chengan Guo, Zeng-Guang Hou, Zhigang Zeng
Place of Publication	Heidelberg [Germany]
Publisher	Springer
Pages	523 - 531
Number of pages	9
ISBN (Electronic)	9783642390654
ISBN (Print)	9783642390647
DOIs	https://doi.org/10.1007/978-3-642-39065-4_63
Publication status	Published - 2013
Event	International Symposium on Neural Networks 2013 - Dalian, China Duration: 4 Jul 2013 → 6 Jul 2013 Conference number: 10th https://link.springer.com/book/10.1007/978-3-642-39065-4 (Conference Proceedings)

Publication series

Name	Lecture Notes in Compute Science
Publisher	Springer
Volume	7951
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	International Symposium on Neural Networks 2013
Abbreviated title	ISNN 2013
Country/Territory	China
City	Dalian
Period	4/07/13 → 6/07/13
Other	Proceedings Part of the Lecture Notes in Computer Science book series (LNCS, volume 7951)
Internet address	https://link.springer.com/book/10.1007/978-3-642-39065-4 (Conference Proceedings)

Keywords

Radon transform
Categorization of visual objects
Chinese characters
Self-organizing maps
Incremental learning

Access to Document

10.1007/978-3-642-39065-4_63

Cite this

Paplinski, A. P. (2013). The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects. In C. Guo, Z-G. Hou, & Z. Zeng (Eds.), Advances in Neural Networks (ISNN 2013): 10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I (pp. 523 - 531). (Lecture Notes in Compute Science; Vol. 7951). Springer. https://doi.org/10.1007/978-3-642-39065-4_63

Paplinski, Andrew P. / The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects. Advances in Neural Networks (ISNN 2013): 10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I. editor / Chengan Guo ; Zeng-Guang Hou ; Zhigang Zeng. Heidelberg [Germany] : Springer, 2013. pp. 523 - 531 (Lecture Notes in Compute Science).

@inproceedings{087c55b6bfcc42cca172fcdc047a15af,

title = "The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects",

abstract = "The recently introduced angular integral of the Radon transform (aniRT) seems to be a good candidate as a feature vector used in categorization of visual objects in a rotation invariant fashion. We investigate application of aniRT in situations when the number of objects is significant, for example, Chinese characters. Typically, the aniRT feature vector spans the diagonal of the visual object. We show that a subset of the full aniRT vector delivers a good categorization results in a timely manner.",

keywords = "Radon transform, Categorization of visual objects, Chinese characters, Self-organizing maps, Incremental learning",

author = "Paplinski, {Andrew P.}",

year = "2013",

doi = "10.1007/978-3-642-39065-4_63",

language = "English",

isbn = "9783642390647",

series = "Lecture Notes in Compute Science",

publisher = "Springer",

pages = "523 -- 531",

editor = "Chengan Guo and Zeng-Guang Hou and Zhigang Zeng",

booktitle = "Advances in Neural Networks (ISNN 2013)",

note = "International Symposium on Neural Networks 2013, ISNN 2013 ; Conference date: 04-07-2013 Through 06-07-2013",

url = "https://link.springer.com/book/10.1007/978-3-642-39065-4",

}

Paplinski, AP 2013, The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects. in C Guo, Z-G Hou & Z Zeng (eds), Advances in Neural Networks (ISNN 2013): 10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I. Lecture Notes in Compute Science, vol. 7951, Springer, Heidelberg [Germany], pp. 523 - 531, International Symposium on Neural Networks 2013, Dalian, China, 4/07/13. https://doi.org/10.1007/978-3-642-39065-4_63

The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects. / Paplinski, Andrew P.

Advances in Neural Networks (ISNN 2013): 10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I. ed. / Chengan Guo; Zeng-Guang Hou; Zhigang Zeng. Heidelberg [Germany] : Springer, 2013. p. 523 - 531 (Lecture Notes in Compute Science; Vol. 7951).

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

TY - GEN

T1 - The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects

AU - Paplinski, Andrew P.

N1 - Conference code: 10th

PY - 2013

Y1 - 2013

N2 - The recently introduced angular integral of the Radon transform (aniRT) seems to be a good candidate as a feature vector used in categorization of visual objects in a rotation invariant fashion. We investigate application of aniRT in situations when the number of objects is significant, for example, Chinese characters. Typically, the aniRT feature vector spans the diagonal of the visual object. We show that a subset of the full aniRT vector delivers a good categorization results in a timely manner.

AB - The recently introduced angular integral of the Radon transform (aniRT) seems to be a good candidate as a feature vector used in categorization of visual objects in a rotation invariant fashion. We investigate application of aniRT in situations when the number of objects is significant, for example, Chinese characters. Typically, the aniRT feature vector spans the diagonal of the visual object. We show that a subset of the full aniRT vector delivers a good categorization results in a timely manner.

KW - Radon transform

KW - Categorization of visual objects

KW - Chinese characters

KW - Self-organizing maps

KW - Incremental learning

U2 - 10.1007/978-3-642-39065-4_63

DO - 10.1007/978-3-642-39065-4_63

M3 - Conference Paper

SN - 9783642390647

T3 - Lecture Notes in Compute Science

SP - 523

EP - 531

BT - Advances in Neural Networks (ISNN 2013)

A2 - Guo, Chengan

A2 - Hou, Zeng-Guang

A2 - Zeng, Zhigang

PB - Springer

CY - Heidelberg [Germany]

T2 - International Symposium on Neural Networks 2013

Y2 - 4 July 2013 through 6 July 2013

ER -

Paplinski AP. The angular integral of the Radon transform (aniRT) as a feature vector in categorization of visual objects. In Guo C, Hou Z-G, Zeng Z, editors, Advances in Neural Networks (ISNN 2013): 10th International Symposium on Neural Networks, ISNN 2013, Dalian, China, July 4-6, 2013, Proceedings, Part I. Heidelberg [Germany]: Springer. 2013. p. 523 - 531. (Lecture Notes in Compute Science). https://doi.org/10.1007/978-3-642-39065-4_63