Running to Get Recognised

Gerard Carty, Muhammad Adil Raja, Conor Ryan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This research investigates the use of Convolutional Neural Networks (CNN) and specifically, You Only Look Once ver. 4 (YOLOv4) to detect Racing Bib Numbers (RBNs) in images from running races and then to recognise the actual numbers using Optical Character Recognition (OCR) techniques. Pre-processing and Tesseract OCR were employed to achieve this. Using a self-acquired private dataset we achieve a recall of 0.91, precision of 0.88, an F1-measure of 0.89, and mean average precision (mAP) of 0.935 for detection. Full number recognition of 71% is then achieved on the successfully detected RBNs. Additionally, the proposed approach attains a very low average inference time of 23.5 ms compared to a previous best recorded time of 750 ms. This is achieved this with a relatively small training set of 1374 images, where previous research used 498,385 labelled images.

Original languageEnglish
Title of host publication6th International Symposium, SIRS 2020, Revised Selected Papers
EditorsSabu M. Thampi, Sri Krishnan, Rajesh M. Hegde, Domenico Ciuonzo, Thomas Hanne, Jagadeesh Kannan R.
PublisherSpringer Science and Business Media Deutschland GmbH
Pages3-17
Number of pages15
ISBN (Print)9789811604249
DOIs
Publication statusPublished - 2021
Event6th International Symposium on Advances in Signal Processing and Intelligent Recognition Systems, SIRS 2020 - Chennai, India
Duration: 14 Oct 202017 Oct 2020

Publication series

NameCommunications in Computer and Information Science
Volume1365
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference6th International Symposium on Advances in Signal Processing and Intelligent Recognition Systems, SIRS 2020
Country/TerritoryIndia
CityChennai
Period14/10/2017/10/20

Keywords

  • Convolutional Neural Networks
  • Machine vision
  • Racing Bib Number

Fingerprint

Dive into the research topics of 'Running to Get Recognised'. Together they form a unique fingerprint.

Cite this