Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 18 of 213
Back to Result List

Intelligent Character Recognition of Handwritten Forms with Deep Neural Networks

  • The automatic processing of handwritten forms remains a challenging task, wherein detection and subsequent classification of handwritten characters are essential steps. We describe a novel approach, in which both steps - detection and classification - are executed in one task through a deep neural network. Therefore, training data is not annotated by hand, but manufactured artificially from theThe automatic processing of handwritten forms remains a challenging task, wherein detection and subsequent classification of handwritten characters are essential steps. We describe a novel approach, in which both steps - detection and classification - are executed in one task through a deep neural network. Therefore, training data is not annotated by hand, but manufactured artificially from the underlying forms and yet existing datasets. It can be demonstrated that this single-task approach is superior in comparison to the state-of-the-art two task approach. The current study focuses on hand-written Latin letters and employs the EMNIST data set. However, limitations were identified with this data set, necessitating further customization. Finally, an overall recognition rate of 88.28% was attained on real data obtained from a written exam.show moreshow less

Export metadata

Statistics

frontdoor_oas
Metadaten
Document Type:Conference Proceeding
Conference Type:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/8296
Bibliografische Angaben
Title (English):Intelligent Character Recognition of Handwritten Forms with Deep Neural Networks
Conference:International TRIZ Future Conference (23. : September 12-14, 2023 : Offenburg, Germany)
Author:Hartwig GrabowskiStaff MemberGND
Edition:1.
Year of Publication:2023
Date of first Publication:2023/08/24
Place of publication:Cham
Publisher:Springer
First Page:81
Last Page:94
Parent Title (English):Towards AI-Aided Invention and Innovation : 23rd International TRIZ Future Conference, TFC 2023, Offenburg, Germany, September 12–14, 2023, Proceedings
Editor:Denis Cavallucci, Pavel Livotov, Stelian Brad
Volume:IFIPAICT 682
ISBN:978-3-031-42531-8 (Hardcover)
ISBN:978-3-031-42534-9 (Softcover)
ISBN:978-3-031-42532-5 (eBook)
ISSN:1868-4238
ISSN:1868-422X (E-ISSN)
DOI:https://doi.org/10.1007/978-3-031-42532-5_6
URL:https://link.springer.com/chapter/10.1007/978-3-031-42532-5_6
Language:English
Inhaltliche Informationen
Institutes:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Institutes:Bibliografie
DDC classes:000 Allgemeines, Informatik, Informationswissenschaft
GND Keyword:Handschrift; Künstliche Intelligenz; Optische Zeichenerkennung
Tag:Deep Neural Network; Handswritten Character Recognition; Yolov5
Formale Angaben
Relevance:Konferenzbeitrag: h5-Index < 30
Open Access: Closed 
Licence (German):License LogoUrheberrechtlich geschützt