Feature extraction CNN algorithms for artificial immune systems

Gy Cserey, A. Falus, W. Porod, T. Roska

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, we introduce some CNN and analogic feature extraction algorithms for artificial immune systems, which are able to convert grayscale or color to binary images storing as much information as possible for further processing. We define a statistical property called immune histogram based on sub-patterns of these images. Our results and measurements show that these algorithms can be implemented in real-time applications. A sample application, which detects new textures in a familiar environment, is also presented.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages147-152
Number of pages6
Volume1
Publication statusPublished - 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary
Duration: Jul 25 2004Jul 29 2004

Other

Other2004 IEEE International Joint Conference on Neural Networks - Proceedings
CountryHungary
CityBudapest
Period7/25/047/29/04

Fingerprint

Immune system
Feature extraction
Binary images
Textures
Color
Processing

ASJC Scopus subject areas

  • Software

Cite this

Cserey, G., Falus, A., Porod, W., & Roska, T. (2004). Feature extraction CNN algorithms for artificial immune systems. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 1, pp. 147-152)

Feature extraction CNN algorithms for artificial immune systems. / Cserey, Gy; Falus, A.; Porod, W.; Roska, T.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 2004. p. 147-152.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cserey, G, Falus, A, Porod, W & Roska, T 2004, Feature extraction CNN algorithms for artificial immune systems. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 1, pp. 147-152, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 7/25/04.
Cserey G, Falus A, Porod W, Roska T. Feature extraction CNN algorithms for artificial immune systems. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1. 2004. p. 147-152
Cserey, Gy ; Falus, A. ; Porod, W. ; Roska, T. / Feature extraction CNN algorithms for artificial immune systems. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 2004. pp. 147-152
@inproceedings{c184ae3933674d058f9782c0aa956778,
title = "Feature extraction CNN algorithms for artificial immune systems",
abstract = "In this paper, we introduce some CNN and analogic feature extraction algorithms for artificial immune systems, which are able to convert grayscale or color to binary images storing as much information as possible for further processing. We define a statistical property called immune histogram based on sub-patterns of these images. Our results and measurements show that these algorithms can be implemented in real-time applications. A sample application, which detects new textures in a familiar environment, is also presented.",
author = "Gy Cserey and A. Falus and W. Porod and T. Roska",
year = "2004",
language = "English",
volume = "1",
pages = "147--152",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - Feature extraction CNN algorithms for artificial immune systems

AU - Cserey, Gy

AU - Falus, A.

AU - Porod, W.

AU - Roska, T.

PY - 2004

Y1 - 2004

N2 - In this paper, we introduce some CNN and analogic feature extraction algorithms for artificial immune systems, which are able to convert grayscale or color to binary images storing as much information as possible for further processing. We define a statistical property called immune histogram based on sub-patterns of these images. Our results and measurements show that these algorithms can be implemented in real-time applications. A sample application, which detects new textures in a familiar environment, is also presented.

AB - In this paper, we introduce some CNN and analogic feature extraction algorithms for artificial immune systems, which are able to convert grayscale or color to binary images storing as much information as possible for further processing. We define a statistical property called immune histogram based on sub-patterns of these images. Our results and measurements show that these algorithms can be implemented in real-time applications. A sample application, which detects new textures in a familiar environment, is also presented.

UR - http://www.scopus.com/inward/record.url?scp=10944228647&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10944228647&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:10944228647

VL - 1

SP - 147

EP - 152

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -