Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/21810
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKumar G.-
dc.contributor.authorKeserwani P.-
dc.contributor.authorPratim Roy, Partha-
dc.contributor.authorDogra D.P.-
dc.date.accessioned2022-03-02T11:41:30Z-
dc.date.available2022-03-02T11:41:30Z-
dc.date.issued2021-
dc.identifier.citationMultimedia Tools and Applications, 80(3): 4341-4365-
dc.identifier.issn13807501-
dc.identifier.urihttps://doi.org/10.1007/s11042-020-09813-6-
dc.identifier.urihttp://repository.iitr.ac.in/handle/123456789/21810-
dc.description.abstractBox level annotation of a large number of logo images for training purpose of typical deep learning architecture is highly challenging. Thus, a method that can detect the logo with the help of training to remove box-level annotations can be helpful. In this paper, we present a method of logo detection that utilizes weakly supervised learning of Convolutional Neural Network (CNN) to generate a deep saliency map. The saliency map is generated from the back-propagated response of the CNN trained with the classification task. The saliency map produces responses for the regions of logos. GrabCut segmentation method has been applied then to obtain the bounding box corresponding to the logo class predicted by the CNN for a given image. AlexNet, CaffeNet, and VGGNet deep architectures has been fine-tuned for the classification purpose. The framework is further utilized for detection through a back-propagated saliency map. The performance of the proposed methodology has been validated on the FlickrLogos-32 logo benchmark dataset. The proposed method outperforms the state-of-the-art baseline fully supervised methods with mean average precision (mAP) of 75.83%. © 2020, Springer Science+Business Media, LLC, part of Springer Nature.-
dc.language.isoen_US-
dc.publisherSpringer-
dc.relation.ispartofMultimedia Tools and Applications-
dc.subjectConvolutional neural network-
dc.subjectGrabCut-
dc.subjectLogo detection-
dc.subjectSaliency map-
dc.subjectWeakly supervised-
dc.titleLogo detection using weakly supervised saliency map-
dc.typeArticle-
dc.scopusid57213515807-
dc.scopusid57205562856-
dc.scopusid56880478500-
dc.scopusid35408975400-
dc.affiliationKumar, G., Department of CSE, Indian Institute of Technology Roorkee, Roorkee, India-
dc.affiliationKeserwani, P., Department of CSE, Indian Institute of Technology Roorkee, Roorkee, India-
dc.affiliationRoy, P.P., Department of CSE, Indian Institute of Technology Roorkee, Roorkee, India-
dc.affiliationDogra, D.P., School of Electrical Sciences, IIT Bhubaneswar, Bhubaneswar, India-
dc.description.fundingThe authors would like to acknowledge the support of DST-SERB. The Project ID is SB/S3/EECE/099/2016. SB/S3/EECE/099/2016-
dc.description.correspondingauthorKumar, G.; Department of CSE, India; email: gautamkumar72@gmail.com-
Appears in Collections:Journal Publications [CS]

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.