COMPARATIVE ANALYSIS OF IMAGES USING DEEP NEURAL NETWORKS
Main Article Content
Abstract
Building a stable system for assessing the similarity of the images is very difficult task. In this paper proposed approach to learning image comparison system that uses techniques of deep learning, namely the combining of all stages of the comparison into one deep neural network. This approach allows one to construct a system that has a much greater training capacity than others. Experimental verification of the system was done on digital images, which represent photos of clothes. Results confirm that the proposed system can improve quality of comparison, as well as reduce the size of the feature vector.
References 15, figures 4, tables 2.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Structure from motion. [Online]. Available: https://en.wikipedia.org/wiki/Structure_from_motion.
R. Hadsell, S. Chopra, and Y. LeCun. Dimensionality reduction by learning an invariant mapping. In CVPR, volume 2, pages 1735–1742. IEEE, 2006. DOI: 10.1109/CVPR.2006.100..
G. W. Taylor, I. Spiro, C. Bregler, and R. Fergus. Learning invariance through imitation. In CVPR, pages 2729–2736. IEEE, 2011. DOI: 10.1109/CVPR.2011.5995538
D. G. Lowe. Object recognition from local scale-invariant features. In ICCV, volume 2, pages 1150–1157. IEEE, 1999. DOI: 10.1109/ICCV.1999.790410
N. Dalal and B. Triggs. Histograms of Oriented Gradients for Human Detection. In CVPR, pages 886–893. IEEE, 2005. DOI: 10.1109/CVPR.2005.177.
Y.-L. Boureau, F. Bach, Y. LeCun, and J. Ponce. Learning mid-level features for recognition. In CVPR, pages 2559–2566. IEEE, 2010. DOI: 10.1109/CVPR.2010.5539963.
A. Krizhevsky, I. Sutskever, and G. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1106–1114, 2012.
Tuytelaars, T and Mikolajczyk, K (2008) Local invariant feature detectors: A survey Foundations and Trends in Computer Graphics and Vision, 3 (3). pp. 177-280.
E. Tola, V.Lepetit, and P. Fua. A Fast Local Descriptor for Dense Matching. In Proceedings of Computer Vision and Pattern Recognition, Alaska, USA, 2008. DOI: 10.1109/CVPR.2008.4587673.
V. Athitsos, J. Alon, S. Sclaroff, and G. Kollios. Boostmap: A method for efficient approximate similarity rankings. In IEEE Conf. on Computer Vision and Pattern Recognition, Madison, WI, June 2004. DOI: 10.1109/CVPR.2004.1315173.
A. S. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson. CNN features off-the-shelf: An astounding baseline for recognition. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR Workshops 2014, Columbus, OH, USA, June 23-28, 2014, pages 512–519, 2014. DOI: 10.1109/CVPRW.2014.131.
P. Fischer, A. Dosovitskiy, and T. Brox. Descriptor matching with convolutional neural networks: a comparison to SIFT, arXiv preprint arXiv:1405.5769, 2014: Available: https://arxiv.org/abs/1405.5769.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, Going deeper with convolutions, arXiv preprint arXiv:1409.4842, 2014. Available: https://arxiv.org/abs/1409.4842.
Hlybynne navchannia [Deep Learning]. Available: https://uk.wikipedia.org/wiki/Глибинне_навчання.
Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell, Caffe: Convolutional architecture for fast feature embedding, arXiv preprint arXiv:1408.5093, 2014. Available: https://arxiv.org/abs/1408.5093.
