Content-Based Image Retrieval using Deep Convolutional Neural Networks

Authors

1 Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran

2 Faculty of Technical and Engineering of Ferdows, University of Birjand, Birjand, Iran

Abstract

Image retrieval is an important issue of machine vision and image processing. Many researches have been done in image retrieval. In 70’s, Text-Based image retrieval had been created before Content-Based image retrieval have been introduced since 90’s cause of large amount of data stored and inefficient previous methods. On this way, researcher reached better conclusion by extracting features from pictures. Semantic gap between these features and human concept, and burst increase in amount of images which were saved, caused researchers to think about new algorithms. Excellent successes on deep learning algorithms encourage us to implant a new method for image retrieval based on deep learning. In this paper, after reviewing deep convolutional neural networks as a kind of deep learning methods, we introduce a new retrieval system based on deep convolutional neural networks and by testing it on three famous databases, ALOI, Corel and MPEG7, computing P(0.5), P(1) and ANMRR and comparing them with other methods which have been used since recent years, we show the superior accuracy of this method in comparison to the other methods.

Keywords


[1] A. N. Tikle, C. Vaidya, and P. Dahiwale, “A survey of indexing techniques for large scale Content-Based image retrieval,” in 2015 International Conference on Electrical, Electronics, Signals,Communication and Optimization (EESCO), pp. 1-5, 2015.
[2] J. A. Silva Júnior, R. E. Marçal and M. A. Batista, “Image retrieval importance and applications,” Workshop de Visao Computacional - WVC 2014, 2014.
[3] R. D. S. Torres and A. X. Falcao, “Content-Based image retrieval theory and applications, ” RITA, vol. 13, no. 2, pp. 161-185, 2006.
[4] Y. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu and M. S. Lew, “Deep learning for visual understanding: A review,” Neurocomputing, vol. 187,  pp. 27-48, 2016.
[5] R.Montagna and G.D.Finlayson, “Padua point interpolation and Lp-norm minimisation in colour-based image indexing and retrieval,” IET Image Processing, vol. 6, no. 2, pp. 139-147, 2012.
[6] H. Farsi and S. Mohamadzadeh, “Colour and texture feature-based image retrieval by using hadamard matrix in discrete wavelet transform,” IET Image Processing, vol. 7, no. 3, pp. 212-218, 2013.
[7] مریم تقی‌زاده، عبداله چاله چاله، «مدلی به‌منظور بازیابی تصویر مبتنی بر چند درخواست»، مجله مهندسی برق دانشگاه تبریز، مقالات آماده انتشار، پذیرفته شده ، انتشار آنلاین از تاریخ 12 فروردین 1396
[8] اسما شمسی گوشکی، سعید سریزدی، حسین نظام آبادی پور،محمد شهرام معین، «روشی جدید در بازخورد ربط برای بازیابی تصویر بر اساس محتوا به شیوه چند پرسشی»، مجله مهندسی برق دانشگاه تبریز، دوره 40، شماره 2، صفحه 51-62، 1389.
[9] D. Varga and T. Szirányi, “Fast content-based image retrieval using convolutional neural network and hash function,” IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2636-2640, 2016.
[10] T. q. Peng and F. Li, “Image retrieval based on deep Convolutional Neural Networks and binary hashing learning,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1742-1746, 2017
[11] A.Qayyum, S.M.Anwar, M.Awais and M.Majid, “Medical image retrieval using deep convolutional neural network,” Neurocomputing, vol. 266,  pp. 8-20, 2017.
[12] H. Liu, B. Li, X. Lv and Y. Huang, “Image retrieval using fused deep convolutional features,” Procedia Computer Science, vol. 107, pp. 749-754, 2017
[13] I. Arel, D. C. Rose and T. P. Karnowski, “Deep machine learning - A new frontier in artificial intelligence research [Research Frontier],” IEEE Computational Intelligence Magazine, vol. 5, no. 4, pp. 13-18, 2010.
[14] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner,“Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86,  no. 11,  pp. 2278-2324, 1998.
[15] A.Krizhevsky, I. Sutskever and G.E.Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems 25, 2012.
[16] H. C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, et al., “Deep convolutional neural networks for Computer-Aided detection: CNN Architectures, Dataset Characteristics and Transfer Learning,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1285-1298, 2016.
[17] Y. D. Chun, N. C. Kim, and I. H. Jang, “Content-Based image retrieval using multiresolution color and texture features,” IEEE Transactions on Multimedia, vol. 10, no. 6, pp. 1073-1084, 2008.
[18] http://caffe.berkeleyvision.org/
[19] S. Mohamadzadeh and H. Farsi, “Content-based image retrieval system via sparse representation,” IET Computer Vision, vol. 10, no. 1, pp. 95-102, 2016.
[20] J. M. Geusebroek, G. J. Burghouts, and A. W. M. Smeulders, “The Amsterdam library of object images,” International Journal Computer Vision,” vol. 61, no. 1, pp. 103-112, 2005.
[21] Corel Database http://wang.ist.psu.edu/docs/related/ (last referred on June, 10th, 2009
[22] I. O. f. Standardisation:, “MPEG-7 overview,” Available at: http://mpeg.chiariglione.org/standards/mpeg-7/mpeg-7.htm, accessed 15 November 2011.