---
_id: '2058'
abstract:
- lang: eng
  text: Nonlinear spatial transforms and fuzzy pattern classification with unimodal
    potential functions are established in signal processing. They have proved to
    be excellent tools in feature extraction and classification. In this paper we
    present a hardware accelerated image processing and classification scheme for
    rotation and translation tolerant two-dimensional pattern recognition, which is
    based on one-dimensional nonlinear discrete circular transforms. However, the
    scheme is simple; it is stable and therefore well suited for industrial applications.
    An implementation on one field programmable gate array (FPGA) is proposed.
author:
- first_name: Tobias
  full_name: Henke, Tobias
  last_name: Henke
- first_name: Volker
  full_name: Lohweg, Volker
  id: '1804'
  last_name: Lohweg
  orcid: 0000-0002-3325-7887
citation:
  ama: 'Henke T, Lohweg V. A Simplified Scheme For Hardware-Based Pattern Recognition.
    In: <i>IEEE International Conference On Image Processing (ICIP), Proceedings</i>.
    Genova: IEEE; 2005:349-352. doi:<a href="https://doi.org/ 10.1109/ICIP.2005.1529759">
    10.1109/ICIP.2005.1529759</a>'
  apa: 'Henke, T., &#38; Lohweg, V. (2005). A Simplified Scheme For Hardware-Based
    Pattern Recognition. In <i>IEEE International Conference On Image Processing (ICIP),
    Proceedings</i> (pp. 349–352). Genova: IEEE. <a href="https://doi.org/ 10.1109/ICIP.2005.1529759">https://doi.org/
    10.1109/ICIP.2005.1529759</a>'
  bjps: '<b>Henke T and Lohweg V</b> (2005) A Simplified Scheme For Hardware-Based
    Pattern Recognition. <i>IEEE International Conference On Image Processing (ICIP),
    Proceedings</i>. Genova: IEEE, pp. 349–352.'
  chicago: 'Henke, Tobias, and Volker Lohweg. “A Simplified Scheme For Hardware-Based
    Pattern Recognition.” In <i>IEEE International Conference On Image Processing
    (ICIP), Proceedings</i>, 349–52. Genova: IEEE, 2005. <a href="https://doi.org/
    10.1109/ICIP.2005.1529759">https://doi.org/ 10.1109/ICIP.2005.1529759</a>.'
  chicago-de: 'Henke, Tobias und Volker Lohweg. 2005. A Simplified Scheme For Hardware-Based
    Pattern Recognition. In: <i>IEEE International Conference On Image Processing
    (ICIP), Proceedings</i>, 349–352. Genova: IEEE. doi:<a href="https://doi.org/
    10.1109/ICIP.2005.1529759,"> 10.1109/ICIP.2005.1529759,</a> .'
  din1505-2-1: '<span style="font-variant:small-caps;">Henke, Tobias</span> ; <span
    style="font-variant:small-caps;">Lohweg, Volker</span>: A Simplified Scheme For
    Hardware-Based Pattern Recognition. In: <i>IEEE International Conference On Image
    Processing (ICIP), Proceedings</i>. Genova : IEEE, 2005, S. 349–352'
  havard: 'T. Henke, V. Lohweg, A Simplified Scheme For Hardware-Based Pattern Recognition,
    in: IEEE International Conference On Image Processing (ICIP), Proceedings, IEEE,
    Genova, 2005: pp. 349–352.'
  ieee: T. Henke and V. Lohweg, “A Simplified Scheme For Hardware-Based Pattern Recognition,”
    in <i>IEEE International Conference On Image Processing (ICIP), Proceedings</i>,
    2005, pp. 349–352.
  mla: Henke, Tobias, and Volker Lohweg. “A Simplified Scheme For Hardware-Based Pattern
    Recognition.” <i>IEEE International Conference On Image Processing (ICIP), Proceedings</i>,
    IEEE, 2005, pp. 349–52, doi:<a href="https://doi.org/ 10.1109/ICIP.2005.1529759">
    10.1109/ICIP.2005.1529759</a>.
  short: 'T. Henke, V. Lohweg, in: IEEE International Conference On Image Processing
    (ICIP), Proceedings, IEEE, Genova, 2005, pp. 349–352.'
  ufg: '<b>Henke, Tobias/Lohweg, Volker (2005)</b>: A Simplified Scheme For Hardware-Based
    Pattern Recognition, in: <i>IEEE International Conference On Image Processing
    (ICIP), Proceedings</i>, Genova, S. 349–352.'
  van: 'Henke T, Lohweg V. A Simplified Scheme For Hardware-Based Pattern Recognition.
    In: IEEE International Conference On Image Processing (ICIP), Proceedings. Genova:
    IEEE; 2005. p. 349–52.'
date_created: 2019-11-29T13:17:49Z
date_updated: 2023-03-15T13:49:38Z
department:
- _id: DEP5023
doi: ' 10.1109/ICIP.2005.1529759'
keyword:
- Pattern recognition
- Field programmable gate arrays
- Neural networks
- Image processing
- Discrete transforms
- Signal processing
- Image retrieval
- Image recognition
- Transient analysis
- Fuzzy systems
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1529759
page: 349 - 352
place: Genova
publication: IEEE International Conference On Image Processing (ICIP), Proceedings
publication_identifier:
  eissn:
  - '2381-8549 '
  isbn:
  - 0-7803-9134-9
  issn:
  - '1522-4880 '
publication_status: published
publisher: IEEE
status: public
title: A Simplified Scheme For Hardware-Based Pattern Recognition
type: conference
user_id: '45673'
year: 2005
...
---
_id: '2056'
abstract:
- lang: eng
  text: Nonlinear spatial transforms and fuzzy pattern classification with unimodal
    potential functions are established in signal processing. They have proved to
    be excellent tools in feature extraction and classification. In this paper, we
    will present a hardware-accelerated image processing and classification system
    which is implemented on one field-programmable gate array (FPGA). Nonlinear discrete
    circular transforms generate a feature vector. The features are analyzed by a
    fuzzy classifier. This principle can be used for feature extraction, pattern recognition,
    and classification tasks. Implementation in radix-2 structures is possible, allowing
    fast calculations with a computational complexity of up to. Furthermore, the pattern
    separability properties of these transforms are better than those achieved with
    the well-known method based on the power spectrum of the Fourier Transform, or
    on several other transforms. Using different signal flow structures, the transforms
    can be adapted to different image and signal processing applications.
author:
- first_name: Volker
  full_name: Lohweg, Volker
  id: '1804'
  last_name: Lohweg
  orcid: 0000-0002-3325-7887
- first_name: Carsten
  full_name: Diederichs, Carsten
  id: '44209'
  last_name: Diederichs
- first_name: Dietmar
  full_name: Müller, Dietmar
  last_name: Müller
citation:
  ama: 'Lohweg V, Diederichs C, Müller D. Algorithms for Hardware-Based Pattern Recognition.
    <i>EURASIP journal on applied signal processing : a publication of the European
    Association for Speech, Signal, and Image Processing </i>. 2004;12(1):1912-1920.
    doi:<a href="https://doi.org/10.1155/S1110865704404247">https://doi.org/10.1155/S1110865704404247</a>'
  apa: 'Lohweg, V., Diederichs, C., &#38; Müller, D. (2004). Algorithms for Hardware-Based
    Pattern Recognition. <i>EURASIP Journal on Applied Signal Processing : A Publication
    of the European Association for Speech, Signal, and Image Processing </i>, <i>12</i>(1),
    1912–1920. <a href="https://doi.org/10.1155/S1110865704404247">https://doi.org/10.1155/S1110865704404247</a>'
  bjps: '<b>Lohweg V, Diederichs C and Müller D</b> (2004) Algorithms for Hardware-Based
    Pattern Recognition. <i>EURASIP journal on applied signal processing : a publication
    of the European Association for Speech, Signal, and Image Processing </i> <b>12</b>,
    1912–1920.'
  chicago: 'Lohweg, Volker, Carsten Diederichs, and Dietmar Müller. “Algorithms for
    Hardware-Based Pattern Recognition.” <i>EURASIP Journal on Applied Signal Processing :
    A Publication of the European Association for Speech, Signal, and Image Processing
    </i> 12, no. 1 (2004): 1912–20. <a href="https://doi.org/10.1155/S1110865704404247">https://doi.org/10.1155/S1110865704404247</a>.'
  chicago-de: 'Lohweg, Volker, Carsten Diederichs und Dietmar Müller. 2004. Algorithms
    for Hardware-Based Pattern Recognition. <i>EURASIP journal on applied signal processing :
    a publication of the European Association for Speech, Signal, and Image Processing
    </i> 12, Nr. 1: 1912–1920. doi:<a href="https://doi.org/10.1155/S1110865704404247,">https://doi.org/10.1155/S1110865704404247,</a>
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Lohweg, Volker</span> ; <span
    style="font-variant:small-caps;">Diederichs, Carsten</span> ; <span style="font-variant:small-caps;">Müller,
    Dietmar</span>: Algorithms for Hardware-Based Pattern Recognition. In: <i>EURASIP
    journal on applied signal processing : a publication of the European Association
    for Speech, Signal, and Image Processing </i> Bd. 12. Akron, Ohio, Hindawi Publ.
    (2004), Nr. 1, S. 1912–1920'
  havard: 'V. Lohweg, C. Diederichs, D. Müller, Algorithms for Hardware-Based Pattern
    Recognition, EURASIP Journal on Applied Signal Processing : A Publication of the
    European Association for Speech, Signal, and Image Processing . 12 (2004) 1912–1920.'
  ieee: 'V. Lohweg, C. Diederichs, and D. Müller, “Algorithms for Hardware-Based Pattern
    Recognition,” <i>EURASIP journal on applied signal processing : a publication
    of the European Association for Speech, Signal, and Image Processing </i>, vol.
    12, no. 1, pp. 1912–1920, 2004.'
  mla: 'Lohweg, Volker, et al. “Algorithms for Hardware-Based Pattern Recognition.”
    <i>EURASIP Journal on Applied Signal Processing : A Publication of the European
    Association for Speech, Signal, and Image Processing </i>, vol. 12, no. 1, Hindawi
    Publ., 2004, pp. 1912–20, doi:<a href="https://doi.org/10.1155/S1110865704404247">https://doi.org/10.1155/S1110865704404247</a>.'
  short: 'V. Lohweg, C. Diederichs, D. Müller, EURASIP Journal on Applied Signal Processing :
    A Publication of the European Association for Speech, Signal, and Image Processing  12
    (2004) 1912–1920.'
  ufg: '<b>Lohweg, Volker et. al. (2004)</b>: Algorithms for Hardware-Based Pattern
    Recognition, in: <i>EURASIP journal on applied signal processing : a publication
    of the European Association for Speech, Signal, and Image Processing </i> <i>12</i>
    (<i>1</i>), S. 1912–1920.'
  van: 'Lohweg V, Diederichs C, Müller D. Algorithms for Hardware-Based Pattern Recognition.
    EURASIP journal on applied signal processing : a publication of the European Association
    for Speech, Signal, and Image Processing . 2004;12(1):1912–20.'
date_created: 2019-11-29T13:09:05Z
date_updated: 2023-03-15T13:49:38Z
department:
- _id: DEP5023
doi: https://doi.org/10.1155/S1110865704404247
intvolume: '        12'
issue: '1'
keyword:
- image processing
- nonlinear circular transforms
- feature extraction
- fuzzy pattern recognition
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://asp-eurasipjournals.springeropen.com/track/pdf/10.1155/S1110865704404247
oa: '1'
page: 1912-1920
place: Akron, Ohio
publication: 'EURASIP journal on applied signal processing : a publication of the
  European Association for Speech, Signal, and Image Processing '
publication_identifier:
  issn:
  - '1110-8657 '
publication_status: published
publisher: Hindawi Publ.
status: public
title: Algorithms for Hardware-Based Pattern Recognition
type: journal_article
user_id: '15514'
volume: 12
year: 2004
...
---
_id: '2053'
abstract:
- lang: ger
  text: In vielen Bereichen der ein- und zweidimensionalen Signalverarbeitung besteht
    die Aufgabe Signale oder Objekte unabhängig von ihren aktuellen Positionen mittels
    geeigneter Merkmale zu klassifizieren. Mit Hilfe schneller nichtlinearer Spektraltransformationen
    ist eine positionsinvariante Merkmalgewinnung möglich. In dieser Arbeit werden
    reelle Transformationen vorgestellt, deren Eigenschaften in Bezug auf verschiedene
    Parameter angepasst werden können. Zu nennen ist das gruppeninvariante Verhalten,
    der rechentechnische Aufwand und die Implementierbarkeit in applikationsspezifische
    Schaltungen. Durch unterschiedliche Berechnungsstrukturen kann beispielsweise
    die Separationseigenschaft aufgabengemäß adaptiert werden. Basierend auf dem Konzept
    charakteristischer Matrizen wird ein generalisiertes Verfahren zur Berechnung
    der Transformationen abgeleitet. Bezüglich ihrer Charakteristika können die vorzustellenden
    Transformationen gegenüber anderen als ebenbürtig oder sogar überlegen bezeichnet
    werden. In Kombination mit einem Fuzzy-Klassifikationsverfahren (Fuzzy-Pattern-Classification,
    FPC) wird ein System-On-Programmable-Chip Mustererkennungssystem entwickelt, das
    auf einem programmierbaren applikationsspezifischen Schaltkreis (FPGA) implementiert
    wird. Das System ist in der Lage pixel-basierende Bilder zu klassifizieren. In
    der Anwendung der Druckbildinspektion erweist sich das Mustererkennungssystem
    als praxisgerecht einsetzbar.
- lang: eng
  text: '    Image retrieval, texture analysis, optical character recognition and
    general inspection tasks are of main interest in the field of image processing
    and pattern recognition. Methods which operate automatically are of interest in
    the above mentioned areas. Therefore, translation invariant transforms are helpful
    tools for pattern recognition tasks. Nonlinear spatial transforms and fuzzy pattern
    classification with unimodal potential functions are established in signal processing.
    They have proved to be excellent tools in feature extraction and classification.
    In this thesis nonlinear discrete transforms, which are adaptable for different
    application tasks, will be presented. The adaptivity includes the group specific
    behaviour, the amount of calculations and the implementability in application
    specific integrated circuits. The pattern separability properties of these transforms
    are better compared to that of the well known power spectrum of the Fourier transform
    and several other known transforms. Furthermore, a hardware accelerator image
    processing and classification system will presented, which is implemented on one
    field programmable gate array (FPGA). The system can be used for feature extraction,
    pattern recognition and classification tasks. In the field of printed image inspection
    the system is applicable under practical aspects.'
alternative_title:
- '    On Effective Implementation of Adaptive Spectral Transforms in Application
  Specific Integrated Circuits'
author:
- first_name: Volker
  full_name: Lohweg, Volker
  id: '1804'
  last_name: Lohweg
  orcid: 0000-0002-3325-7887
citation:
  ama: 'Lohweg V. <i>Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise</i>. Chemnitz: Technische
    Universität Chemnitz; 2003.'
  apa: 'Lohweg, V. (2003). <i>Ein Beitrag zur effektiven Implementierung adaptiver
    Spektraltransformationen in applikationsspezifische integrierte Schaltkreise</i>.
    Chemnitz: Technische Universität Chemnitz.'
  bjps: '<b>Lohweg V</b> (2003) <i>Ein Beitrag zur effektiven Implementierung adaptiver
    Spektraltransformationen in applikationsspezifische integrierte Schaltkreise</i>.
    Chemnitz: Technische Universität Chemnitz.'
  chicago: 'Lohweg, Volker. <i>Ein Beitrag zur effektiven Implementierung adaptiver
    Spektraltransformationen in applikationsspezifische integrierte Schaltkreise</i>.
    Chemnitz: Technische Universität Chemnitz, 2003.'
  chicago-de: 'Lohweg, Volker. 2003. <i>Ein Beitrag zur effektiven Implementierung
    adaptiver Spektraltransformationen in applikationsspezifische integrierte Schaltkreise</i>.
    Chemnitz: Technische Universität Chemnitz.'
  din1505-2-1: '<span style="font-variant:small-caps;">Lohweg, Volker</span>: <i>Ein
    Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen in applikationsspezifische
    integrierte Schaltkreise</i>. Chemnitz : Technische Universität Chemnitz, 2003'
  havard: V. Lohweg, Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise, Technische Universität Chemnitz,
    Chemnitz, 2003.
  ieee: 'V. Lohweg, <i>Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise</i>. Chemnitz: Technische
    Universität Chemnitz, 2003.'
  mla: Lohweg, Volker. <i>Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise</i>. Technische Universität
    Chemnitz, 2003.
  short: V. Lohweg, Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise, Technische Universität Chemnitz,
    Chemnitz, 2003.
  ufg: '<b>Lohweg, Volker (2003)</b>: Ein Beitrag zur effektiven Implementierung adaptiver
    Spektraltransformationen in applikationsspezifische integrierte Schaltkreise,
    Chemnitz.'
  van: 'Lohweg V. Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
    in applikationsspezifische integrierte Schaltkreise. Chemnitz: Technische Universität
    Chemnitz; 2003. 207 p.'
date_created: 2019-11-29T12:54:10Z
date_updated: 2023-03-15T13:49:38Z
ddc:
- '620'
department:
- _id: DEP5023
keyword:
- ASIC
- Abbildungseigenschaft
- Druckbildkontrolle
- Prozessorelement
- Systolisches Array
- Fuzzy-Maß
- Invarianz
- Klassifikation
- Mehrdimensionale Bildverarbeitung
- Mustererkennung
- Nichtlineare Transformation
language:
- iso: ger
main_file_link:
- open_access: '1'
  url: https://nbn-resolving.org/urn:nbn:de:swb:ch1-200400031
oa: '1'
page: '207'
place: Chemnitz
publication_status: published
publisher: Technische Universität Chemnitz
status: public
supervisor:
- first_name: Dietmar
  full_name: Müller, Dietmar
  last_name: Müller
- first_name: Gerd
  full_name: Scarbata, Gerd
  last_name: Scarbata
- first_name: Norman
  full_name: Bitterlin, Norman
  last_name: Bitterlin
title: Ein Beitrag zur effektiven Implementierung adaptiver Spektraltransformationen
  in applikationsspezifische integrierte Schaltkreise
type: dissertation
user_id: '45673'
year: 2003
...