Publikation: A Deep-Learning Based Visual Sensing Co...

Stammdaten
Titel: A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions
Untertitel:
Kurzfassung: This paper’s core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc. Document classification is a special machine vision task in which document images are categorized according to their likelihood. Document classification is by itself an important topic for the digital office and it has several usages. Additionally, different methods for solving this problem have been presented in various studies; their respectively reached performance is however not yet good enough. This task is very tough and challenging. Thus, a novel, more accurate and precise model is needed. Although the related works do reach acceptable accuracy values for less hard conditions, they generally fully fail in the face of those above-mentioned hard, real-world conditions, including, amongst others, distortions such as noise, blur, low contrast, and shadows. In this paper, a novel deep CNN model is developed, validated and benchmarked with a selection of the most relevant recent document classification models. Additionally, the model’s sensitivity was significantly improved by injecting different artifacts during the training process. In the benchmarking, it does clearly outperform all others by at least 4%, thus reaching more than 96% accuracy.
Schlagworte: Electrical and Electronic Engineering, Biochemistry, Instrumentation, Atomic and Molecular Physics, and Optics, Analytical Chemistry
Publikationstyp: Beitrag in Zeitschrift (Autorenschaft)
Erscheinungsdatum: 12.10.2021 (Online)
Erschienen in: Sensors
Sensors
zur Publikation
 ( MDPI Publishing; )
Titel der Serie: -
Bandnummer: 21
Heftnummer: 20
Erstveröffentlichung: Ja
Version: -
Seite: -
Gesamtseitenanzahl: 6763 S.

Versionen
Keine Version vorhanden
Erscheinungsdatum: 12.10.2021
ISBN (e-book): -
eISSN: 1424-8220
DOI: http://dx.doi.org/10.3390/s21206763
Homepage: https://www.mdpi.com/1424-8220/21/20/6763
Open Access
  • Online verfügbar (Open Access)

Zuordnung
Organisation Adresse
Fakultät für Technische Wissenschaften
  Institut für Intelligente Systemtechnologien
Universitätsstraße 65-67
9020 Klagenfurt am Wörthersee
Österreich
   hubert.zangl@aau.at
http://www.uni-klu.ac.at/tewi/ict/sst/index.html
zur Organisation
Universitätsstraße 65-67
AT - 9020  Klagenfurt am Wörthersee

Kategorisierung
Sachgebiete
  • 102003 - Bildverarbeitung
  • 102018 - Künstliche Neuronale Netze
  • 102019 - Machine Learning
Forschungscluster
  • Selbstorganisierende Systeme
  • Humans in the Digital Age
Zitationsindex
  • Science Citation Index Expanded (SCI Expanded)
Informationen zum Zitationsindex: Master Journal List
Peer Reviewed
  • Ja
Publikationsfokus
  • Science to Science (Qualitätsindikator: I)
Klassifikationsraster der zugeordneten Organisationseinheiten:
Arbeitsgruppen
  • Transportation Informatics Group

Kooperationen
Organisation Adresse
Université de Kinshasa
Kinshasa
Kongo, Demokrat.Republik
CD  Kinshasa

Beiträge der Publikation
Keine verknüpften Publikationen vorhanden