Refine
Document Type
Conference Type
- Konferenzartikel (1)
Has Fulltext
- no (2) (remove)
Is part of the Bibliography
- yes (2)
Keywords
- Deep Neural Network (1)
- Handschrift (1)
- Handswritten Character Recognition (1)
- Künstliche Intelligenz (1)
- Optische Zeichenerkennung (1)
- Physical Distancing (1)
- Social Distancing (1)
- Spacial Anchors (1)
- Yolov5 (1)
Open Access
- Closed (1)
- Open Access (1)
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 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.
Es wird ein neuer Ansatz zur Bestimmung des Abstands zweier oder mehrerer Smartphones zueinander vorgestellt. Dabei wird die Position des jeweiligen Smartphones im Raum bzw. im Gelände bezüglich eines Referenzpunkts (Spatial Anchor Point) ermittelt. Über einen zentralen Server tauschen die Smartphones ihre Position relativ zum Referenzpunkt aus und können daraus die Abstände zueinander berechnen. Unterschreitet der Abstand zweier Smartphones einen Schwellwert (< 2 m), erfolgt eine entsprechende Signalisierung auf den Smartphones.