Vehicle tire (tyre) detection and text recognition using deep learning

Wajahat Kazmi, Ian Nabney, George Vogiatzis, Peter Rose, Alexander Codd

Research output: Chapter in Book/Report/Conference proceedingConference publication

Abstract

This paper presents an industrial system to read text on tire sidewalls. Images of vehicle tires in motion are acquired using roadside cameras. Firstly, the tire circularity is detected using Circular Hough Transform (CHT) with dynamic radius detection. The tire is then unwarped into a rectangular patch and a cascade of convolutional neural network (CNN) classifiers is applied for text recognition. We introduce a novel proposal generator for localizing the tire code by combining Histogram of Oriented Gradients (HOG) with a CNN. The proposals are then filtered using a deep network. After the code is localized, character detection and recognition are carried out using two separate deep CNNs. The system presents impressive accuracy and efficiency proving its suitability for the intended industrial application.
Original languageEnglish
Title of host publication2019 IEEE 15th International Conference on Automation Science and Engineering, CASE 2019
PublisherIEEE
Pages1074-1079
Number of pages6
Volume2019-August
ISBN (Electronic)9781728103556
ISBN (Print)978-1-7281-0357-0
DOIs
Publication statusE-pub ahead of print - 19 Sep 2019
Event2019 IEEE 15th International Conference on Automation Science and Engineering (CASE) - Vancouver, BC, Canada
Duration: 22 Aug 201926 Aug 2019

Publication series

Name2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)
PublisherIEEE
ISSN (Print)2161-8070
ISSN (Electronic)2161-8089

Conference

Conference2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)
Period22/08/1926/08/19

Bibliographical note

Funding: Innovate UK under the Knowledge Transfer Partnership (KTP) Grant No. KTP009834.

Fingerprint Dive into the research topics of 'Vehicle tire (tyre) detection and text recognition using deep learning'. Together they form a unique fingerprint.

Cite this