Reconstruction Old Students Image Using The Autoencoder Method

Ahmad Azhari, Candra Putra Negara, Azmi Badhi'uz Zaman, Dimas Aji Setiawan

Abstract


Image Processing is image processing with a digital computer to produce new images according to the user's wishes. One implementation is to reconstruct the image. Through the extraction stages can get the characteristics of an image. The algorithm used is Adam Optimization, an extension of the stochastic gradient reduction that has seen wider adoption for deep learning applications in computer vision and natural language processing. In this study, we use the autoencoder technique, one variant of artificial neural networks generally used to "encode" data. The autoencoder is trained to produce the same output as the input. This image reconstruction aims to process an image whose quality is not very clear, to be precise. This, if possible, can be used to detect someone's face from photos. In reconstructing this image through the encode and decode process by defining Conv2D and Maxpool, it is processed into training with epoch 100 times while for the prediction process using Keras library. Then, the last one gets an accuracy of 0,022. The result is the output of the reconstructed image and calculation graph

Full Text:

PDF

References


M. Engelcke, O. P. Jones, and I. Posner, “Reconstruction bottlenecks in Object-Centric generative models,” arXiv preprint arXiv:2007.06245. 2020.

A. Dolmatova, M. Chukalina, and D. Nikolaev, “Accelerated FBP for computed tomography image reconstruction,” in 2020 IEEE International Conference on Image Processing (ICIP), IEEE, 2020, pp. 3030–3034.

J. H. Nam and A. Velten, “Super-resolution remote imaging using time encoded remote apertures,” Appl. Sci., vol. 10, no. 18, p. 6458, 2020.

N. Ailon, O. Leibovitch, and V. Nair, “Sparse linear networks with a fixed butterfly structure: theory and practice,” in Uncertainty in Artificial Intelligence, PMLR, 2021, pp. 1174–1184.

O. Wiles, S. Ehrhardt, and A. Zisserman, “Co-attention for conditioned image matching,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 15920–15929.

D. Minnen and S. Singh, “Channel-wise autoregressive entropy models for learned image compression,” in 2020 IEEE International Conference on Image Processing (ICIP), IEEE, 2020, pp. 3339–3343.

W. Lee, J. Lee, D. Kim, and B. Ham, “Learning with privileged information for efficient image super-resolution,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16, Springer, 2020, pp. 465–482.

J. Tang, C. Huang, J. Liu, and H. Zhu, “Image super-resolution based on CNN using multilabel gene expression programming,” Appl. Sci., vol. 10, no. 3, p. 854, 2020.

M. G. Hu, J. F. Wang, and Y. Ge, “Super-resolution reconstruction of remote sensing images using multifractal analysis,” Sensors, vol. 9, no. 11, pp. 8669–8683, 2009.

Y. Zhang, W. Miao, Z. Lin, H. Gao, and S. Shi, “Millimeter-wave InSAR image reconstruction approach by total variation regularized matrix completion,” Remote Sens., vol. 10, no. 7, p. 1053, 2018.

S. Indolia, A. K. Goswami, S. P. Mishra, and P. Asopa, “Conceptual understanding of convolutional neural network-a deep learning approach,” Procedia Comput. Sci., vol. 132, pp. 679–688, 2018.

T. Sun, W. Fang, W. Chen, Y. Yao, F. Bi, and B. Wu, “High-resolution image inpainting based on multi-scale neural network,” Electronics, vol. 8, no. 11, p. 1370, 2019.




DOI: http://dx.doi.org/10.17977/um010v6i22023p1-5

Refbacks

  • There are currently no refbacks.


 

 Letters in Information Technology Education (LITE)
 2654-5667
 Contact
 Published by Electrical Engineering, Universitas Negeri   Malang, Indonesia
 Jl. Semarang No. 5 Malang, East Java, Indonesia
 Homepage:  http://journal2.um.ac.id/index.php/lite/index
 E-mail: lite.teum@gmail.com

View My Stats