Pattern recognition system invariant to rotation and scale to identify color images

Angel Coronel-Beltrán

doi:10.1063/1.4897703

Pattern recognition system invariant to rotation and scale to identify color images

Angel Coronel-Beltrán^*

^*Corresponding author for this work

Departamento de Investigación en Física

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

Abstract

This work presents a pattern recognition digital system based on nonlinear correlations. The correlation peak values given by the system were analyzed by the peak-to-correlation energy (PCE) metric to determine the optimal value of the non-linear coefficient kin the k-law. The system was tested with 18 different color images of butterflies; each image was rotated from 0° to 180° with increments of 1° and scaled ±25% with increments of 1% and to take advantage of the color property of the images the RGB model was employed. The boxplot statistical analysis of the mean with ±2∗EE (standard errors) for the PCE values set that the system invariant to rotation and scale has a confidence level at least of 95.4%.

Original language	English
Title of host publication	International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014
Editors	Theodore E. Simos, Theodore E. Simos, Theodore E. Simos, Theodore E. Simos, Theodore E. Simos, Zacharoula Kalogiratou, Theodore Monovasilis
Publisher	American Institute of Physics Inc.
Pages	151-154
Number of pages	4
ISBN (Electronic)	9780735412552
DOIs	https://doi.org/10.1063/1.4897703
State	Published - 6 Oct 2014
Event	International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014 - Athens, Greece Duration: 4 Apr 2014 → 7 Apr 2014

Publication series

Name	AIP Conference Proceedings
Volume	1618
ISSN (Print)	0094-243X
ISSN (Electronic)	1551-7616

Conference

Conference	International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014
Country/Territory	Greece
City	Athens
Period	4/04/14 → 7/04/14

Bibliographical note

Publisher Copyright:
© 2014 AIP Publishing LLC.

Keywords

Pattern recognition
color model
digital correlation
nonlinear filter

Access to Document

10.1063/1.4897703

Cite this

Coronel-Beltrán, A. (2014). Pattern recognition system invariant to rotation and scale to identify color images. In T. E. Simos, T. E. Simos, T. E. Simos, T. E. Simos, T. E. Simos, Z. Kalogiratou, & T. Monovasilis (Eds.), International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014 (pp. 151-154). (AIP Conference Proceedings; Vol. 1618). American Institute of Physics Inc.. https://doi.org/10.1063/1.4897703

Coronel-Beltrán, Angel. / Pattern recognition system invariant to rotation and scale to identify color images. International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014. editor / Theodore E. Simos ; Theodore E. Simos ; Theodore E. Simos ; Theodore E. Simos ; Theodore E. Simos ; Zacharoula Kalogiratou ; Theodore Monovasilis. American Institute of Physics Inc., 2014. pp. 151-154 (AIP Conference Proceedings).

@inproceedings{48c753a9f66e4c55833f2b6fc9c9a16f,

title = "Pattern recognition system invariant to rotation and scale to identify color images",

abstract = "This work presents a pattern recognition digital system based on nonlinear correlations. The correlation peak values given by the system were analyzed by the peak-to-correlation energy (PCE) metric to determine the optimal value of the non-linear coefficient kin the k-law. The system was tested with 18 different color images of butterflies; each image was rotated from 0° to 180° with increments of 1° and scaled ±25% with increments of 1% and to take advantage of the color property of the images the RGB model was employed. The boxplot statistical analysis of the mean with ±2∗EE (standard errors) for the PCE values set that the system invariant to rotation and scale has a confidence level at least of 95.4%.",

keywords = "Pattern recognition, color model, digital correlation, nonlinear filter",

author = "Angel Coronel-Beltr{\'a}n",

note = "Publisher Copyright: {\textcopyright} 2014 AIP Publishing LLC.; International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014 ; Conference date: 04-04-2014 Through 07-04-2014",

year = "2014",

month = oct,

day = "6",

doi = "10.1063/1.4897703",

language = "Ingl{\'e}s",

series = "AIP Conference Proceedings",

publisher = "American Institute of Physics Inc.",

pages = "151--154",

editor = "Simos, {Theodore E.} and Simos, {Theodore E.} and Simos, {Theodore E.} and Simos, {Theodore E.} and Simos, {Theodore E.} and Zacharoula Kalogiratou and Theodore Monovasilis",

booktitle = "International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014",

}

Coronel-Beltrán, A 2014, Pattern recognition system invariant to rotation and scale to identify color images. in TE Simos, TE Simos, TE Simos, TE Simos, TE Simos, Z Kalogiratou & T Monovasilis (eds), International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014. AIP Conference Proceedings, vol. 1618, American Institute of Physics Inc., pp. 151-154, International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014, Athens, Greece, 4/04/14. https://doi.org/10.1063/1.4897703

Pattern recognition system invariant to rotation and scale to identify color images. / Coronel-Beltrán, Angel.
International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014. ed. / Theodore E. Simos; Theodore E. Simos; Theodore E. Simos; Theodore E. Simos; Theodore E. Simos; Zacharoula Kalogiratou; Theodore Monovasilis. American Institute of Physics Inc., 2014. p. 151-154 (AIP Conference Proceedings; Vol. 1618).

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

TY - GEN

T1 - Pattern recognition system invariant to rotation and scale to identify color images

AU - Coronel-Beltrán, Angel

PY - 2014/10/6

Y1 - 2014/10/6

N2 - This work presents a pattern recognition digital system based on nonlinear correlations. The correlation peak values given by the system were analyzed by the peak-to-correlation energy (PCE) metric to determine the optimal value of the non-linear coefficient kin the k-law. The system was tested with 18 different color images of butterflies; each image was rotated from 0° to 180° with increments of 1° and scaled ±25% with increments of 1% and to take advantage of the color property of the images the RGB model was employed. The boxplot statistical analysis of the mean with ±2∗EE (standard errors) for the PCE values set that the system invariant to rotation and scale has a confidence level at least of 95.4%.

AB - This work presents a pattern recognition digital system based on nonlinear correlations. The correlation peak values given by the system were analyzed by the peak-to-correlation energy (PCE) metric to determine the optimal value of the non-linear coefficient kin the k-law. The system was tested with 18 different color images of butterflies; each image was rotated from 0° to 180° with increments of 1° and scaled ±25% with increments of 1% and to take advantage of the color property of the images the RGB model was employed. The boxplot statistical analysis of the mean with ±2∗EE (standard errors) for the PCE values set that the system invariant to rotation and scale has a confidence level at least of 95.4%.

KW - Pattern recognition

KW - color model

KW - digital correlation

KW - nonlinear filter

UR - http://www.scopus.com/inward/record.url?scp=84947543807&partnerID=8YFLogxK

U2 - 10.1063/1.4897703

DO - 10.1063/1.4897703

M3 - Contribución a la conferencia

AN - SCOPUS:84947543807

T3 - AIP Conference Proceedings

SP - 151

EP - 154

BT - International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014

A2 - Simos, Theodore E.

A2 - Kalogiratou, Zacharoula

A2 - Monovasilis, Theodore

PB - American Institute of Physics Inc.

T2 - International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014

Y2 - 4 April 2014 through 7 April 2014

ER -

Coronel-Beltrán A. Pattern recognition system invariant to rotation and scale to identify color images. In Simos TE, Simos TE, Simos TE, Simos TE, Simos TE, Kalogiratou Z, Monovasilis T, editors, International Conference of Computational Methods in Sciences and Engineering 2014, ICCMSE 2014. American Institute of Physics Inc. 2014. p. 151-154. (AIP Conference Proceedings). doi: 10.1063/1.4897703

Pattern recognition system invariant to rotation and scale to identify color images

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this