Multi-Label Logo Classification using Convolutional Neural Networks
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/122954
Title: | Multi-Label Logo Classification using Convolutional Neural Networks |
---|---|
Authors: | Gallego, Antonio-Javier | Pertusa, Antonio | Bernabeu, Marisa |
Research Group/s: | Reconocimiento de Formas e Inteligencia Artificial |
Center, Department or Service: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos |
Keywords: | Logo image retrieval | Multi-Label Classification | Convolutional Neural Networks |
Knowledge Area: | Lenguajes y Sistemas Informáticos |
Issue Date: | 22-Sep-2019 |
Publisher: | Springer, Cham |
Citation: | Gallego, AJ., Pertusa, A., Bernabeu, M. (2019). Multi-label Logo Classification Using Convolutional Neural Networks. In: Morales, A., Fierrez, J., Sánchez, J., Ribeiro, B. (eds) Pattern Recognition and Image Analysis. IbPRIA 2019. Lecture Notes in Computer Science(), vol 11867. Springer, Cham. https://doi.org/10.1007/978-3-030-31332-6_42 |
Abstract: | The classification of logos is a particular case within computer vision since they have their own characteristics. Logos can contain only text, iconic images or a combination of both, and they usually include figurative symbols designed by experts that vary substantially besides they may share the same semantics. This work presents a method for multi-label classification and retrieval of logo images. For this, Convolutional Neural Networks (CNN) are trained to classify logos from the European Union TradeMark (EUTM) dataset according to their colors, shapes, sectors and figurative designs. An auto-encoder is also trained to learn representations of the input images. Once trained, the neural codes from the last convolutional layers in the CNN and the central layer of the auto-encoder can be used to perform similarity search through kNN, allowing us to obtain the most similar logos based on their color, shape, sector, figurative elements, overall features, or a weighted combination of them provided by the user. To the best of our knowledge, this is the first multi-label classification method for logos, and the only one that allows retrieving a ranking of images with these criteria provided by the user. |
Sponsor: | This work is supported by the Spanish Ministry HISPAMUS project with code TIN2017-86576-R, partially funded by the EU. |
URI: | http://hdl.handle.net/10045/122954 |
ISBN: | 978-3-030-31331-9 | 978-3-030-31332-6 |
DOI: | 10.1007/978-3-030-31332-6_42 |
Language: | eng |
Type: | info:eu-repo/semantics/conferenceObject |
Rights: | © 2019 Springer Nature Switzerland AG |
Peer Review: | si |
Publisher version: | https://doi.org/10.1007/978-3-030-31332-6_42 |
Appears in Collections: | INV - GRFIA - Comunicaciones a Congresos, Conferencias, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Gallego_etal_IbPRIA 2019_preprint.pdf | Preprint (acceso abierto) | 3,27 MB | Adobe PDF | Open Preview |
Gallego_etal_IbPRIA 2019_final.pdf | Versión final (acceso restringido) | 4,49 MB | Adobe PDF | Open Request a copy |
Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.