SIAMESE NEURAL NETWORKS
DOI:
https://doi.org/10.24867/09BE10StojanovicKeywords:
Siamese neural networks, artificial intelli¬gence, image recognitionAbstract
In this paper an experiment in character identification with two different Siamese neural networks is presented, along with the effects of affine transformations on training and testing. Two different Siamese neural networks were implemented and tested in different scenarios. In most scenarios results showed high precision. Guidelines for future research are also presented.
References
[1] Koch, G., Zemel, R. and Salakhutdinov, R., 2015. “Siamese neural networks for one-shot image recognition.” In ICML deep learning workshop (Vol. 2).
[2] de Oliveira, I.O., Fonseca, K.V. and Minetto, R., 2019. “A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras.” arXiv preprint arXiv:1902.01496.
[3] Wu, L., Wang, Y., Gao, J. and Li, X., 2018. “Where-and-when to look: Deep siamese attention networks for video-based person re-identification.” IEEE Transactions on Multimedia, 21(6), pp.1412-1424.
[4] Wiggers, K.L., Britto Jr, A.S., Heutte, L., Koerich, A.L. and Oliveira, L.S., 2019. “Image Retrieval and Pattern Spotting using Siamese Neural Network.” arXiv preprint arXiv:1906.09513.
[5] Jose, A., Yan, S. and Heisterklaus, I., 2017, September. “Binary hashing using siamese neural networks.” In 2017 IEEE International Conference on Image Processing (ICIP) (pp. 2916-2920). IEEE.
[6] https://keras.io/examples/mnist_siamese/ (приступљено 13.8.2019.)
[7] Hadsell, Raia, Sumit Chopra, and Yann LeCun. “Dimensionality reduction by learning an invariant mapping.” In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), vol. 2, pp. 1735-1742. IEEE, 2006.
[8] https://lutzroeder.github.io/netron/ (приступљено 9.1.2020.)
[2] de Oliveira, I.O., Fonseca, K.V. and Minetto, R., 2019. “A Two-Stream Siamese Neural Network for Vehicle Re-Identification by Using Non-Overlapping Cameras.” arXiv preprint arXiv:1902.01496.
[3] Wu, L., Wang, Y., Gao, J. and Li, X., 2018. “Where-and-when to look: Deep siamese attention networks for video-based person re-identification.” IEEE Transactions on Multimedia, 21(6), pp.1412-1424.
[4] Wiggers, K.L., Britto Jr, A.S., Heutte, L., Koerich, A.L. and Oliveira, L.S., 2019. “Image Retrieval and Pattern Spotting using Siamese Neural Network.” arXiv preprint arXiv:1906.09513.
[5] Jose, A., Yan, S. and Heisterklaus, I., 2017, September. “Binary hashing using siamese neural networks.” In 2017 IEEE International Conference on Image Processing (ICIP) (pp. 2916-2920). IEEE.
[6] https://keras.io/examples/mnist_siamese/ (приступљено 13.8.2019.)
[7] Hadsell, Raia, Sumit Chopra, and Yann LeCun. “Dimensionality reduction by learning an invariant mapping.” In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), vol. 2, pp. 1735-1742. IEEE, 2006.
[8] https://lutzroeder.github.io/netron/ (приступљено 9.1.2020.)
Downloads
Published
2020-08-26
Issue
Section
Electrotechnical and Computer Engineering
