Reconstruction Low- Resolution Image Face Using Restricted Boltzmann Machine

Julian Supardi

Abstract

Low-resolution (LR) face images are one of the most challenging problems in face recognition (FR) systems. Due to the difficulty of finding the specific features of faces, the accuracy of face recognition is low. To solve this problem, some researchers are using an image reconstruction approach to improve the resolution of their images. In this research, we are trying to use the restricted Boltzmann machine (RBM) to solve the problem. Furthermore, a labelled face in the wild (lfw) database has been used to validate the proposed method. The results of the experiment show that the PSNR and SSIM of the image result are 34.05 dB and 96.8%, respectively.

Full Text:

PDF

References

References

Jian, M., &Lam, K. M. (2015). Simultaneous hallucination and recognition of low-resolution faces based on singular value decomposition. IEEE Transactions on Circuits and Systems for Video Technology, 25(11), 1761–1772.

Li, J., Zhao, B., &Zhang, H. (2009). Face recognition based on PCA and LDA combination feature extraction. 2009 First International Conference on Information Science and Engineering, (20042013), 1240–1243.

Zou, W. W. W., &Yuen, P. C. (2012). Very low resolution face recognition problem. IEEE Transactions on Image Processing, 21(1), 327–340.

Yang, R., Wang, Y., Yang, D., Xu, T., &Zhou, J. (2011). Face hallucination via using the graph-optimal locality preserving projections. 2011 10th IEEE/ACIS International Conference on Computer and Information Science, 189–193.

Yang, C. Y., Liu, S., &Yang, M. H. (2013). Structured face hallucination. Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1099–1106.

An, L., & Bhanu, B. (2014). Face image super-resolution using 2D CCA. Signal Processing, 103, 184–194.

Biswas, S., Aggarwal, G., Flynn, P. J., &Bowyer, K. W. (2013). Pose-robust recognition of low-resolution face images, 35(12), 3037–3049.

Park, J. S., &Lee, S. W. (2008). An example-based face hallucination method for single-frame, low-resolution facial images. IEEE Transactions on Image Processing, 17(10), 1806–1816.

Ren, C. X., Dai, D. Q., &Yan, H. (2012). Coupled kernel embedding for low-resolution face image recognition. IEEE Transactions on Image Processing, 21(8), 3770–3783.

Zhao, W., Chellappa, R., Phillips, P. J., &Rosenfeld, a. (2003). Face recognition: A literature survey. Acm Computing Surveys, 35(4), 399–458.

Wang, Z., Miao, Z., Jonathan Wu, Q. M., Wan, Y., &Tang, Z. (2014). Low-resolution face recognition: A review. Visual Computer, 30(4), 359–386.

Fischer, A., &Igel, C. (2014). Training restricted Boltzmann machines: An introduction. Pattern Recognition, 47(1), 25–39.

Fischer, A., &Igel, C. (2012). An introduction to restricted Boltzmann machines. Lecture Notes in Computer Science: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 7441, 14–36.

Hinton, G. E., Salakhutdinov, R. R.. (2006) . Reducing the dimensionality of data with neural networks. SCIENCE, Vol. 313, Issue 5786, 2006, 504-507.

Larochelle, H., &Bengio, Y. (2008). Classification using discriminative restricted Boltzmann machines. Icml, 536–543.

Salakhutdinov, R., Mnih, A., &Hinton, G. (2007). Restricted Boltzmann machines for collaborative filtering. Proceedings of the 24th International Conference on Machine Learning - ICML ’07, 791–798.

Zheng, X., Wu, Z., Meng, H., Li, W., &Cai, L. (2013). Feature learning with Gaussian restricted Boltzmann machine for robust speech recognition. arXiv:1309.6176 [cs.CL]

Tran, S. N., Wolff, D., Weyde, T., &Garcez, A. (2014). Feature preprocessing with RBMs for music similarity learning. AES 53th, 1–8.

Ranzato, M. A., &Hinton, G. E. (2010). Factored 3-way restricted Boltzmann machines for modeling natural images. Artificial Intelligence, 9, 621–628.

Salakhutdinov, R., &Hinton, G. (2009). Deep Boltzmann machines. Aistats, 1(3), 448–455.

Bengio. Y.,(2009). Learning deep architectures for AI.Foundations and Trends®in Machine Learning. Vol. 2, No. 1 (2009) 1–127

Sahasrabudhe, M., &Namboodiri, A. M. (2014). Fingerprint enhancement using unsupervised hierarchical feature learning. Proc. of the 2014 Indian Conference on Computer Vision Graphics and Image Processing - ICVGIP ’14, 1–8.

Hinton, G. (2014). Boltzmann machines. Encyclopedia of Machine Learning and Data Mining, (1), 1–7.

Fischer, A., &Igel, C. (2014). Training restricted Boltzmann machines. Pattern Recogn., 47(1), 25–39.

Cho, K. H. (2011). Improved learning algorithms for restricted Boltzmann machines. Master’s thesis, Aalto University School of Science.

Hinton, G. E. (2002). Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8), 1771–1800.

Welling, M. Product of experts. Scholarpedia 2(10), 3879 (2007)

LeRoux, N., &Bengio, Y. (2008). Representational power of restricted Boltzmann machines and deep belief networks. Neural Computation, 20(6), 1631–1649.

Montufar, G., &Ay, N. (2010). Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines, (2010), 1–12.

Restricted Boltzmann Machines (RBM) — DeepLearning 0.1 documentation

Yildirim, I. (2012). Bayesian inference: Gibbs sampling, 14627, 1–6.

Hinton, G. (2010). A practical guide to training restricted Boltzmann machines. Computer, 9(3), 1.

Huang, G. B., Jain, V., &Learned-Miller, E. (2007). Unsupervised joint alignment of complex images. Proceedings of the IEEE International Conference on Computer Vision.

Huang, G. B., Mattar, M. A., Lee, H., &Learned-Miller, E. (2012). Learning to align from scratch. Proc. Neural Information Processing Systems, 1–9.

DOI: https://doi.org/10.36706/sjia.v4i1.72

Refbacks

  • There are currently no refbacks.