TY - GEN
T1 - Running to Get Recognised
AU - Carty, Gerard
AU - Raja, Muhammad Adil
AU - Ryan, Conor
N1 - Publisher Copyright:
© 2021, Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Convolutional Neural Networks
KW - Machine vision
KW - Racing Bib Number
UR - http://www.scopus.com/inward/record.url?scp=85102506059&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-0425-6_1
DO - 10.1007/978-981-16-0425-6_1
M3 - Conference contribution
AN - SCOPUS:85102506059
SN - 9789811604249
T3 - Communications in Computer and Information Science
SP - 3
EP - 17
BT - 6th International Symposium, SIRS 2020, Revised Selected Papers
A2 - Thampi, Sabu M.
A2 - Krishnan, Sri
A2 - Hegde, Rajesh M.
A2 - Ciuonzo, Domenico
A2 - Hanne, Thomas
A2 - Kannan R., Jagadeesh
PB - Springer Science and Business Media Deutschland GmbH
T2 - 6th International Symposium on Advances in Signal Processing and Intelligent Recognition Systems, SIRS 2020
Y2 - 14 October 2020 through 17 October 2020
ER -