Abstract
The paper contributes to the CBIR systems applied to trademark retrieval. The proposed method seeks to find dynamically the best feature extractor that represents the trademark queried. In the experiments are applied four feature extractors: Concavity/Convexity deficiencies (CC), Freeman Chain (FC), Scale Invariant Feature Transform (SIFT) and Hu Invariant Moments (Hu). These extractors represent a set of classes of features extractors, which are submitted to a classification process using two different classifiers: ANN (Artificial Neural Networks) and SVM (Support Vector Machines). The selecting the best feature extractor is important to processing the next levels in search of similar trademarks (i.e. applying zoning mechanisms or combining the best feature extractors), because it is possible restrict the number of operations in large databases. We carried out experiments using UK Patent Office database, with 10,151 images. Our results are in the same basis of the literature and the average in the best case for the normalized recall (Rn) is equal to 0.91. Experiments show that dynamic selection of extractors can contribute to improve the trademarks retrieval.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Eakins, J.P., Boardman, J.M., Graham, M.E.: Similarity retrieval of trademarks image. IEEE Multimedia 5, 53–63 (1998)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Cerri, A., Ferri, M., Gioirgi, D.: Retrieval of trademarks images by means of size functions. Graph. Models 68(5–6), 451–471 (2006)
Abe, K., Iguchi, H., Tian, H., Roy, D.: Recognition of plural grouping patterns in trademarks for CBIR according to the Gestalt psychology. Inst. Eletron. Inf. Commun. Eng. 89(6), 1798–1805 (2006)
Haitao, R., Yeli, L., Likun, L.: Single closed contour trademark classification based on support vector machine. In: 3rd International Congress on Image and Signal Processing (CISP), pp. 1942–1946 (2010)
Rufino, H.L.P.: Algoritmo de Aprendizado Supervisionado - Baseado em Máquina de Vetores de Suporte - Uma contribuição Para o Reconhecimento de Dados Desbalanceados. Universidade Federal de Uberlândia. Tese de Doutorado (2011)
Anuar, F.M., Setchi, R., Yu-Kun, L.: Trademark image retrieval using an integrated shape descriptor. Expert Sys. Appl. 40(1), 105–121 (2013)
Sahbi, H., Ballan, L., Serra, G., Bimbo, A.D.: Context-dependent logo matching and recognition. IEEE Trans. Image Process. 22(3), 1018–1030 (2013)
Aires, S.B.K., Freitas, C.O.A., Oliveira, L.S.: Feature Analysis for Content-based Trademark Retrieval. In: 27th International Conference on Computer Applications in Industry and Engineering, New Orleans, USA, pp. 245–249 (2014)
Liu, Y.: Sistema de recomendação dos amigos na rede social online baseado em Máquinas de Vetores Suporte. Dissertação de Mestrado. UnB, Brasília (2014)
Aires, S.B.K., Freitas, C.O.A., Soares, L.E.O.: SIFT applied to perceptual zoning for trademark retrieval. In: IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015), v. 1 (2015)
Kumar, R., Tripathi, R.C., Tiwari, M.D.: A comprehensive study on content based trademark retrieval system. Int. J. Comput. Appl. 13, 18–22 (2011)
Shaaban, Z.: Trademark image retrieval system using neural network. Int. J. Comput. Sci. Netw. (IJCSN) 3, 73–82 (2014)
Wu, J.K., Lam, C.P., Mehtre, B.M., Gao, Y.J., Narasimhalu, A.: Content based retrieval for trademark registration. Multimedia Tools Appl. 3(3), 245–267 (1996)
Aker, C., Tursun, O., Kalkan, S. :Analyzing deep features for trademark retrieval. In: 25th Signal Processing and Communications Applications Conference (SIU) (2017)
Chang, C.C., Lin, C.J.: LIBSVM - a library for support vector machines. Disponível em http://www.csie.ntu.edu.tw/~cjlin/libsvm. Acessado em 07 de maio de 2018
INTELLECTUAL Property Office. Disponível em http://www.ipo.gov.uk/. Acesso em 20 de junho de 2018
Acknowledgments
The authors wish to thanks the CAPES, Federal Technological University of Parana (UTFPR-PG, Brazil) and Pontifical Catholic University of Parana (PUCPR, Brazil), which have supported this work.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Aires, S.B.K., Freitas, C.O.A., Sguario, M.L. (2018). Dynamic Selection Feature Extractor for Trademark Retrieval. In: Batyrshin, I., Martínez-Villaseñor, M., Ponce Espinosa, H. (eds) Advances in Soft Computing. MICAI 2018. Lecture Notes in Computer Science(), vol 11288. Springer, Cham. https://doi.org/10.1007/978-3-030-04491-6_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-04491-6_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04490-9
Online ISBN: 978-3-030-04491-6
eBook Packages: Computer ScienceComputer Science (R0)