Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/5592
Title: A deep one-shot network for query-based logo retrieval
Authors: Bhunia A.K.
Bhunia A.K.
Ghose S.
Das A.
Roy P.P.
Pal U.
Published in: Pattern Recognition
Abstract: Logo detection in real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. These methods do not satisfy the incremental demand of logo classes necessary for practical deployment since it is practically impossible to have such annotated data for new unseen logo. In this work, we develop an easy-to-implement query-based logo detection and localization system by employing a one-shot learning technique using off the shelf neural network components. Given an image of a query logo, our model searches for logo within a given target image and predicts the possible location of the logo by estimating a binary segmentation mask. The proposed model consists of a conditional branch and a segmentation branch. The former gives a conditional latent representation of the given query logo which is combined with feature maps of the segmentation branch at multiple scales in order to obtain the matching location of the query logo in a target image. Feature matching between the latent query representation and multi-scale feature maps of segmentation branch using simple concatenation operation followed by 1 × 1 convolution layer makes our model scale-invariant. Despite its simplicity, our query-based logo retrieval framework achieved superior performance in FlickrLogos-32 and TopLogos-10 dataset over different existing baseline methods. © 2019
Citation: Pattern Recognition (2019), 96(): -
URI: https://doi.org/10.1016/j.patcog.2019.106965
http://repository.iitr.ac.in/handle/123456789/5592
Issue Date: 2019
Publisher: Elsevier Ltd
Keywords: Logo retrieval
Multi-scale conditioning
One-shot learning
Query retrieval
Similarity matching
ISSN: 313203
Author Scopus IDs: 57188719920
57203526133
57209826260
57211301249
56880478500
57200742116
Author Affiliations: Bhunia, A.K., University of Surrey, England, United Kingdom
Bhunia, A.K., Jadavpur University, India
Ghose, S., Institute of Engineering & Management, India
Das, A., Institute of Engineering & Management, India
Roy, P.P., Indian Institute of Technology Roorkee, India
Pal, U., Indian Statistical Institute, India
Corresponding Author: Roy, P.P.; Indian Institute of Technology RoorkeeIndia; email: proy.fcs@iitr.ac.in
Appears in Collections:Journal Publications [CS]

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


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