Trademark image recognition utilizing deep convolutional neural network

M. Haddad*, A. Saleh, Y. Jaber

Department of Electrical Engineering, School of Engineering, The University of Jordan, Amman, Jordan

Abstract

The purpose of this work is taking into account major challenges of trademark recognition i.e., reduction in semantic gap, attaining more accuracy, reduction in computation complexity by implementing trademark image retrieval through deep Convolutional Neural Networks (CNNs) integrated with relevance feedback mechanism. The dataset features are optimized through Particle swam optimization (PSO); reducing the search space. These best/optimized features are given to the self-organizing map (SOM) for clustering at the preprocessing stage, The CNN model is trained on feature representations of relevant and irrelevant images, using the feedback information from the user bringing the marked relevant images closer to the query. Experimentation proves significant performance by using FlickrLogos-32 PLUS dataset, as illustrated within the performance results section.

Keywords

Content-based image retrieval, Deep convolutional neural networks, Particle, swarm optimization, Self-organizing map

Digital Object Identifier (DOI)

https://doi.org/10.21833/AEEE.2019.03.003

Article history

Received 12 October 2018, Received in revised form 2 February 2019, Accepted 15 February 2019

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Haddad M, Saleh A, and Jaber Y (2019). Trademark image recognition utilizing deep convolutional neural network. Annals of Electrical and Electronic Engineering, 2(3): 13-20

References (23)

  1. Alaei A and Delalandre M (2014). A complete logo detection/recognition system for document images. In the 11th IAPR International Workshop on Document Analysis Systems, IEEE, Loire Valley, France: 324-328. https://doi.org/10.1109/DAS.2014.79   [Google Scholar]
  2. Bagheri MA, Gao Q, and Escalera S (2013). Logo recognition based on the dempster-shafer fusion of multiple classifiers. In the Canadian Conference on Artificial Intelligence. Springer, Berlin, Heidelberg, Germany: 1-12. https://doi.org/10.1007/978-3-642-38457-8_1   [Google Scholar]
  3. Bai Q (2010). Analysis of particle swarm optimization algorithm. Computer and Information Science, 3(1): 180-184. https://doi.org/10.5539/cis.v3n1p180   [Google Scholar]
  4. Bao Y, Li H, Fan X, Liu R, and Jia Q (2016). Region-based CNN for logo detection. In the International Conference on Internet Multimedia Computing and Service, ACM, Xian, China: 319-322. https://doi.org/10.1145/3007669.3007728   [Google Scholar]
  5. Bianco S, Buzzelli M, Mazzini D, and Schettini R (2015). Logo recognition using cnn features. In the International Conference on Image Analysis and Processing, Springer, Berlin, Heidelberg, Germany: 438-448. https://doi.org/10.1007/978-3-319-23234-8_41   [Google Scholar]
  6. Eggert C, Winschel A, and Lienhart R (2015). On the benefit of synthetic data for company logo detection. In Proceedings of the 23rd ACM International Conference on Multimedia, ACM, Brisbane, Australia: 1283-1286. https://doi.org/10.1145/2733373.2806407   [Google Scholar]
  7. Feng D, Siu WC, and Zhang HJ (2013). Multimedia information retrieval and management: Technological fundamentals and applications. In: Long F, Zhang H, and Feng DD (Eds.), Fundamentals of content-based image retrieval: 1-26. Springer Science and Business Media, Berlin, Heidelberg, Germany.   [Google Scholar]
  8. Hoi SC, Wu X, Liu H, Wu Y, Wang H, Xue H, and Wu Q (2015). Logo-net: Large-scale deep logo detection and brand recognition with deep region-based convolutional networks. arXiv preprint, arXiv:1511.02462.   [Google Scholar]
  9. Iandola FN, Shen A, Gao P, and Keutzer K (2015). Deeplogo: Hitting logo recognition with the deep neural network hammer. arXiv preprint, arXiv:1510.02131.   [Google Scholar]
  10. Kameyama K, Oka N, and Toraichi K (2006). Optimal parameter selection in image similarity evaluation algorithms using particle swarm optimization. In the IEEE International Conference on Evolutionary Computation, IEEE, Vancouver, Canada: 1079-1086. https://doi.org/10.1109/CEC.2006.1688429   [Google Scholar]
  11. Laaksonen J, Koskela M, Laakso S, and Oja E (2001). Self-organising maps as a relevance feedback technique in content-based image retrieval. Pattern Analysis and Applications, 4(2-3): 140-152. https://doi.org/10.1007/PL00014575   [Google Scholar]
  12. Ma L, Lin L, and Gen M (2012). A PSO-SVM approach for image retrieval and clustering. In the 41st International Conference on Computers and Industrial Engineering, Los Angeles, California, USA: 629-634.   [Google Scholar]
  13. Okayama M, Oka N, and Kameyama K (2007). Relevance optimization in image database using feature space preference mapping and particle swarm optimization. In the International Conference on Neural Information Processing. Springer, Berlin, Heidelberg, Germany: 608-617. https://doi.org/10.1007/978-3-540-69162-4_63   [Google Scholar]
  14. Revaud J, Douze M, and Schmid C (2012). Correlation-based burstiness for logo retrieval. In the 20th ACM International Conference on Multimedia, ACM, Nara, Japan: 965-968. https://doi.org/10.1145/2393347.2396358   [Google Scholar]
  15. Romberg S and Lienhart R (2013). Bundle min-hashing for logo recognition. In the 3rd ACM Conference on International Conference on Multimedia Retrieval, ACM, Dallas, Texas, USA: 113-120. https://doi.org/10.1145/2461466.2461486   [Google Scholar]
  16. Romberg S, Pueyo LG, Lienhart R, and Van Zwol R (2011). Scalable logo recognition in real-world images. In the 1st ACM International Conference on Multimedia Retrieval, ACM, Trento, Italy: 25-32. https://doi.org/10.1145/1991996.1992021   [Google Scholar]
  17. Su JH, Huang WJ, Philip SY, and Tseng VS (2011). Efficient relevance feedback for content-based image retrieval by mining user navigation patterns. IEEE Transactions on Knowledge and Data Engineering, 23(3): 360-372. https://doi.org/10.1109/TKDE.2010.124   [Google Scholar]
  18. Su Z, Zhang H, Li S, and Ma S (2003). Relevance feedback in content-based image retrieval: Bayesian framework, feature subspaces, and progressive learning. IEEE Transactions on Image Processing, 12(8): 924-937. https://doi.org/10.1109/TIP.2003.815254   [Google Scholar]
  19. Suganthan PN (2002). Shape indexing using self-organizing maps. IEEE Transactions on Neural Networks, 13(4): 835-840. https://doi.org/10.1109/TNN.2002.1021884   [Google Scholar]
  20. Tzelepi M and Tefas A (2016). Relevance feedback in deep convolutional neural networks for content based image retrieval. In the 9th Hellenic Conference on Artificial Intelligence, ACM, Thessaloniki, Greece. https://doi.org/10.1145/2903220.2903240   [Google Scholar]
  21. Vesanto J, Himberg J, Alhoniemi E, and Parhankangas J (1999). Self-organizing map in Matlab: The SOM Toolbox. In the Matlab DSP Conference, 99: 16-17.   [Google Scholar]
  22. Wang Z and Hong K (2012). A novel approach for trademark image retrieval by combining global features and local features. Journal of Computational Information Systems, 8(4): 1633-1640.   [Google Scholar]
  23. Xue B, Zhang M, and Browne WN (2013). Particle swarm optimization for feature selection in classification: A multi-objective approach. IEEE Transactions on Cybernetics, 43(6): 1656-1671. https://doi.org/10.1109/TSMCB.2012.2227469   [Google Scholar]