Rotation invariant categorization of visual objects using Radon transform and self-organizing modules

Andrew Peter Paplinski

doi:10.1007/978-3-642-17534-3_44

Rotation invariant categorization of visual objects using Radon transform and self-organizing modules

Andrew Peter Paplinski

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

8 Citations (Scopus)

Abstract

The Radon transform in combination with self-organizing maps is used to build the rotation invariant systems for categorization of visual objects. The first system has one SOM per the Radon transform direction. The outputs from these directional SOMs that represent positions of the winners and related post-synaptic activities, form the input to the final categorizing SOM. Such a network delivers robust rotation invariant categorization of images rotated by angles up to around 12o. In the second network the angular Radon transform vectors are combined together and form the input to the categorizing SOM. This network can correctly categorized visual stimuli rotated by up to 30o. The rotation invariance can be improved by increasing the number of Radon transform angle, which has been equal to six in our initial experiments.

Original language	English
Title of host publication	Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications
Editors	Kok Wai Wong, B Sumudu U Mendis, Abdesselam Bouzerdoum
Place of Publication	Berlin Germany
Publisher	Springer-Verlag London Ltd.
Pages	360 - 366
Number of pages	7
Volume	6444
ISBN (Print)	9783642175336
DOIs	https://doi.org/10.1007/978-3-642-17534-3_44
Publication status	Published - 2010
Event	International Conference on Neural Information Processing 2010 - Sydney, Australia Duration: 22 Nov 2010 → 25 Nov 2010 Conference number: 17th https://link.springer.com/book/10.1007/978-3-642-17537-4 (Proceedings)

Conference

Conference	International Conference on Neural Information Processing 2010
Abbreviated title	ICONIP 2010
Country/Territory	Australia
City	Sydney
Period	22/11/10 → 25/11/10
Internet address	https://link.springer.com/book/10.1007/978-3-642-17537-4 (Proceedings)

Access to Document

10.1007/978-3-642-17534-3_44

Cite this

Paplinski, A. P. (2010). Rotation invariant categorization of visual objects using Radon transform and self-organizing modules. In K. W. Wong, B. S. U Mendis, & A. Bouzerdoum (Eds.), Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications (Vol. 6444, pp. 360 - 366). Springer-Verlag London Ltd.. https://doi.org/10.1007/978-3-642-17534-3_44

Paplinski, Andrew Peter. / Rotation invariant categorization of visual objects using Radon transform and self-organizing modules. Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications. editor / Kok Wai Wong ; B Sumudu U Mendis ; Abdesselam Bouzerdoum. Vol. 6444 Berlin Germany : Springer-Verlag London Ltd., 2010. pp. 360 - 366

@inproceedings{5476240d40b24658839c581b02cc20ea,

title = "Rotation invariant categorization of visual objects using Radon transform and self-organizing modules",

abstract = "The Radon transform in combination with self-organizing maps is used to build the rotation invariant systems for categorization of visual objects. The first system has one SOM per the Radon transform direction. The outputs from these directional SOMs that represent positions of the winners and related post-synaptic activities, form the input to the final categorizing SOM. Such a network delivers robust rotation invariant categorization of images rotated by angles up to around 12o. In the second network the angular Radon transform vectors are combined together and form the input to the categorizing SOM. This network can correctly categorized visual stimuli rotated by up to 30o. The rotation invariance can be improved by increasing the number of Radon transform angle, which has been equal to six in our initial experiments.",

author = "Paplinski, {Andrew Peter}",

year = "2010",

doi = "10.1007/978-3-642-17534-3_44",

language = "English",

isbn = "9783642175336",

volume = "6444",

pages = "360 -- 366",

editor = "Wong, {Kok Wai} and {U Mendis}, {B Sumudu} and Abdesselam Bouzerdoum",

booktitle = "Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications",

publisher = "Springer-Verlag London Ltd.",

address = "Germany",

note = "International Conference on Neural Information Processing 2010, ICONIP 2010 ; Conference date: 22-11-2010 Through 25-11-2010",

url = "https://link.springer.com/book/10.1007/978-3-642-17537-4",

}

Paplinski, AP 2010, Rotation invariant categorization of visual objects using Radon transform and self-organizing modules. in KW Wong, BS U Mendis & A Bouzerdoum (eds), Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications. vol. 6444, Springer-Verlag London Ltd., Berlin Germany, pp. 360 - 366, International Conference on Neural Information Processing 2010, Sydney, New South Wales, Australia, 22/11/10. https://doi.org/10.1007/978-3-642-17534-3_44

Rotation invariant categorization of visual objects using Radon transform and self-organizing modules. / Paplinski, Andrew Peter.
Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications. ed. / Kok Wai Wong; B Sumudu U Mendis; Abdesselam Bouzerdoum. Vol. 6444 Berlin Germany: Springer-Verlag London Ltd., 2010. p. 360 - 366.

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

TY - GEN

T1 - Rotation invariant categorization of visual objects using Radon transform and self-organizing modules

AU - Paplinski, Andrew Peter

N1 - Conference code: 17th

PY - 2010

Y1 - 2010

N2 - The Radon transform in combination with self-organizing maps is used to build the rotation invariant systems for categorization of visual objects. The first system has one SOM per the Radon transform direction. The outputs from these directional SOMs that represent positions of the winners and related post-synaptic activities, form the input to the final categorizing SOM. Such a network delivers robust rotation invariant categorization of images rotated by angles up to around 12o. In the second network the angular Radon transform vectors are combined together and form the input to the categorizing SOM. This network can correctly categorized visual stimuli rotated by up to 30o. The rotation invariance can be improved by increasing the number of Radon transform angle, which has been equal to six in our initial experiments.

AB - The Radon transform in combination with self-organizing maps is used to build the rotation invariant systems for categorization of visual objects. The first system has one SOM per the Radon transform direction. The outputs from these directional SOMs that represent positions of the winners and related post-synaptic activities, form the input to the final categorizing SOM. Such a network delivers robust rotation invariant categorization of images rotated by angles up to around 12o. In the second network the angular Radon transform vectors are combined together and form the input to the categorizing SOM. This network can correctly categorized visual stimuli rotated by up to 30o. The rotation invariance can be improved by increasing the number of Radon transform angle, which has been equal to six in our initial experiments.

UR - http://springerlink.com/content/h61368825001pu83/

U2 - 10.1007/978-3-642-17534-3_44

DO - 10.1007/978-3-642-17534-3_44

M3 - Conference Paper

SN - 9783642175336

VL - 6444

SP - 360

EP - 366

BT - Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications

A2 - Wong, Kok Wai

A2 - U Mendis, B Sumudu

A2 - Bouzerdoum, Abdesselam

PB - Springer-Verlag London Ltd.

CY - Berlin Germany

T2 - International Conference on Neural Information Processing 2010

Y2 - 22 November 2010 through 25 November 2010

ER -

Paplinski AP. Rotation invariant categorization of visual objects using Radon transform and self-organizing modules. In Wong KW, U Mendis BS, Bouzerdoum A, editors, Proceedings of the 17th International Conference on Neural Information Processing: Models and Applications. Vol. 6444. Berlin Germany: Springer-Verlag London Ltd. 2010. p. 360 - 366 doi: 10.1007/978-3-642-17534-3_44

Rotation invariant categorization of visual objects using Radon transform and self-organizing modules

Abstract

Conference

Access to Document

Other files and links

Cite this