• Treffer 1 von 1
Zurück zur Trefferliste

Racing Bib Number Recognition Using Neural Networks

  • The goal of this research is to investigate the use of deep convolutional neural networks for racing bib number recognition in sport images. Several deep neural network architectures are studied. Three final architectures are trained on three different sets of data: 1) Street View House Numbers (SVHN) Dataset, 2) A private dataset from Flashframe.io from different running events, and 3) A combination of dataset 1 and 2. This thesis investigates the performance that can be obtained on racing bib numbers from a neural network that has been trained on solely images from street house numbers, on a mixture of SVHN and RBN images as well as only on RBN images. The motivation behind this is to see how well this problem can be solved by transfer learning, as labelled images of racing bib numbers are scarce. The models are tested on the RBNR Dataset (Ben-Ami et al., 2012) and a subset of the private dataset from Flashframe.io. The study shows that the best recognition results were obtained by a model trained on the hybrid dataset of all SVHN images plus an additional 50.000 images. This model outperformed the models that had been trained solely on the SVHN Dataset or the private racing bib number dataset. The best model resulted in Recall of 0,92, Precision of 0,93 and F-measure of 0,93 on the RBNR Dataset (using the same formulas as previously reported on the RBNR dataset), and 0,97, 0,97 and 0,97 on the private dataset, respectively. The reported recognition results on the RBNR dataset are much higher than previously used methods and proves that neural networks can effectively be used for racing bib number recognition.

Volltext Dateien herunterladen

  • Ivarsson,Erica_MA_2019.pdf
    eng

    verfügbar innerhalb des Netzes der HWR Berlin

Metadaten exportieren

Weitere Dienste

Teilen auf Twitter Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor/Autorin:Erica Ivarsson
Erstgutachter/Erstgutachterin:Roland Müller
Zweitgutachter/Zweitgutachterin:Markus Löcher
Dokumentart:Masterarbeit
Sprache:Englisch
Datum der Erstveröffentlichung:13.08.2019
Veröffentlichende Institution:Hochschulbibliothek HWR Berlin
Titel verleihende Institution:Hochschule für Wirtschaft und Recht Berlin
Datum der Abschlussprüfung:06.02.2019
Datum der Freischaltung:13.08.2019
Freies Schlagwort / Tag:CNN; DCNN; Deep Learning; Digit Recognition in Natural Scene Images; Multi-Digit Recognition; Neural Networks; RBNR; Racing Bib Number Detection; SVHN; Transfer Learning
Seitenzahl:112
Fachbereiche und Studiengänge:FB I - Wirtschaftswissenschaften / Business Intelligence and Process Management M.Sc.
Lizenz (Deutsch):License LogoUrheberrechtsschutz