Recognition of low-resolution building images using deep learning and softmax

Authors

  • Leandro Aureliano da Silva
  • Eduardo Silva Vasconcelos
  • Edilberto Pereira Teixeira
  • Antonio Manoel Batista da Silva
  • Marcelo Lucas
  • Lúcio Rogério Júnior
  • Florisvaldo Cardozo Bomfim Júnior
  • Luiz Fernando Ribeiro de Paiva

DOI:

https://doi.org/10.55905/oelv21n9-203

Keywords:

autoencoder, building recognition, deep learning, softmax

Abstract

Image recognition of buildings has been gaining attention in recent years due to the growing popularity of georeferencing tools and their use in the areas of tourism and navigation. The use of mobile devices is critical in these applications and, therefore, processing should be fast and allow the use of low-resolution images. However, many options to perform this task use highly complex recognition techniques. Thus, the great difficulty is that these images are obtained from different angles, under different lighting conditions, in addition to partial obstructions from trees, moving vehicles, or other buildings that hinder recognition. To bypass these problems, this work aims to use the Deep Stacked Autoencoder in the extraction and reduction of features, the Softmax classifier in the recognition and the same deep learning technique applied to the classifier that uses the multilayer perceptron network for comparison purposes with Softmax software. To verify the efficiency of the method, a database of images of buildings from the University of Shefield was used. The algorithm proved to be efficient in the recognition task, reaching 94.9% accuracy.

References

Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neurais networks. Advances in neural information processing systems. 2012.

Hall, Patrick. An Efficient Pattern Recognition Approach with Applications. SAS3100-2016, SAS Institute Inc (2016).

J. Li and N. M. Allinson. Building Recognition Using Local Oriented Features. IEEE Transactions on Industrial Informatics, vol. 9, no. 3, pp. 1697-1704, Aug. 2013.

J. Li and N. M. Allinson. Subspace learning-based dimensionality reduction in building recognition. Neuro computing, vol. 73, no. 1–3, pp. 324–330, 2009.

R. Hutchings and W. Mayol-Cuevas. Building recognition for mobile devices: Incorporating positional information with visual features. Comput. Sci., Univ. Bristol, Bristol, U.K.,Tech. Rep. CSTR-06-017, 2005.

W. Zhang, J. Kosecka. Localization based on building recognition. IEEE Workshop Appl. Visually Impaired (2005) 21–28.

N. Groeneweg, B. Groot, A. Halma, B. Quiroga, M. Tromp, and F. Groen. A fast offline building recognition application on a mobile telephone. Adv. Concepts Intell. Vis. Syst., pp. 1122–1132, 2006.

Y. Li, L.G. Shapiro. Consistent line clusters for building recognition in CBIR. IEEE Int. Conf. Pattern Recognition 3 (2002) 952–956.

H.-H. Trinh, D.-N. Kim, and K.-H. Jo. Facet-based multiple building analysis for robot intelligence. J. Appl. Math. Computation, vol. 205, no. 2, pp. 537–549, 2008.

W. Duan, N. M. Allinson. Vanishing Points Detection and Line Grouping for Complex Building Façade Identification. WSCG, p. 213-220, 2010.

Y.-C. Chung, T. X. Han, and Z. He. Building recognition using sketchbased representations and spectral graph matching. IEEE Int. Conf. Comput. Vis., 2009, pp. 2014–2020.

T.S.H. Shao, L.V. Gool, Zubud-Zurich buildings database for image based recognition. Technique Report No. 260, Swiss Federal Institute of Technology, 2003.

J. Li, W. Huang, L. Shao and N. M. Allinson, Building recognition in urban environments: A survey of state-of-the-art and future challenges. Information Sciences, vol. 277, pp. 406-420, 2014.

J. Zabalza, J. C. Ren, J. B. Zheng, H. M. Zhao, C. M. Qing, Z. J. Yang. Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging. Neurocomputing, vol. 185, pp. 1-10, Apr 2016.

M. Kan, S. Shan, H. Chang, and X. Chen. Stacked progressive auto-encoders (spae) for face recognition across poses. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1883–1890, 2014.

B. A. Olshausen and D. J. Field. Sparse coding with an overcomplete basis set: a strategy employed by V1? Vision Research, 37:3311–3325, December 1997.

Lincoln. http://eprints.lincoln.ac.uk/id/eprint/16079/, Lincoln, 2023.

Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H. B., & dos Reis Alves, S. F. Artificial Neural Networks: A Practical Course. Springer, 2016.

Tang, Yichuan. Deep learning using linear support vector machines. arXiv preprint arXiv:1306.0239 (2013).

Silva, Leandro Aureliano, et al. Building recognition using the gabor filter, the wavelet transform and the multilayer perceptron neural network. Brazilian Journal of Development 8.5 (2022): 35182-35199 (publised in portuguese language).

Downloads

Published

2023-09-29

How to Cite

da Silva , L. A., Vasconcelos , E. S., Teixeira , E. P., da Silva, A. M. B., Lucas , M., Rogério Júnior , L., Bomfim Júnior , F. C., & de Paiva , L. F. R. (2023). Recognition of low-resolution building images using deep learning and softmax . OBSERVATÓRIO DE LA ECONOMÍA LATINOAMERICANA, 21(9), 14288–14308. https://doi.org/10.55905/oelv21n9-203

Issue

Section

Articles

Most read articles by the same author(s)