Deep learning for logo detection

Simple item page
dc.contributor.authorPaleček, Karel
dc.date.accessioned2019-10-15T15:25:01Z
dc.date.available2019-10-15T15:25:01Z
dc.date.issued2019
dc.description.abstractWe present a deep learning system for automatic logo detection in real world images. We base our detector on the popular framework of FasterR-CNN and compare its performance to other models such as Mask R-CNN or RetinaNet. We perform a detailed empirical analysis of various design and architecture choices and show how these can have much higher influence than algorithmic tweaks or popular techniques such as data augmentation. We also provide a systematic detection performance comparison of various models on multiple popular datasets including FlickrLogos-32, TopLogo-10 and recently introduced QMUL-OpenLogo benchmark, which allows for a direct comparison between recently proposed extensions. By careful optimization of the training procedure we were able to achieve significant improvements of the state of the art on all mentioned datasets. We apply our observations to build a detector to detect logos of the Red Bull brand in online media and images.cs
dc.identifier.doi10.1109/TSP.2019.8769038
dc.identifier.urihttps://dspace.tul.cz/handle/15240/154034
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8769038
dc.language.isocscs
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof2019 42nd International Conference on Telecommunications and Signal Processing, TSP 2019
dc.subjectFaster R-CNNcs
dc.subjectFlickrLogos-32cs
dc.subjectLogo detectioncs
dc.subjectMask R-CNNcs
dc.subjectQMUl-OpenLogocs
dc.subjectRetinaNetcs
dc.subjectTopLogo-10cs
dc.titleDeep learning for logo detectioncs
dc.typeConference Paper
local.article.number8769038
local.citation.epage612
local.citation.spage609
local.event.edate2019-07-03
local.event.locationRadisson Blu Beke HotelSuperior, 43. Terez krt.Budapest; Hungary
local.event.sdate2019-07-01
local.event.title42nd International Conference on Telecommunications and Signal Processing, TSP 2019
local.identifier.publikace7160
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Deep learning for logo detection.pdf
Size:
85.5 KB
Format:
Adobe Portable Document Format
Description:
článek
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections