Image compression module based neural network autoencoders

V.O. Lesyk, А.Yu. Doroshenko


A new approach is proposed to data compression in the form of a neural network module based on the structure of autoencoders, which has the most optimal learning time, compression level and obtains sufficiently clear image reconstruction. The main mechanisms for building the structure of encoder and decoder neural networks, which are used as a module, have been developed. The main data for the reconstruction were selected from the open data set Fashion-MNIST, which allows simplified testing of neural network structures, the process of their training and obtaining results. Approaches to image reproduction using neural network layers of convolution and inverse convolution are analyzed. An analysis of the impact on the quality of the resulting image reconstruction of the structure of the output module, which is used to compress the input image, was carried out. Atypical behavior was found during the increase of layers in the structure of the autoencoder, which did not lead to an increase in the quality of image reproduction. The basic necessity of changing the structural parts of the autoencoder and its application in combination with other technologies to obtain a better reproduction result and the elimination of distortions is highlighted.

Prombles in programming 2023; 1: 48-57


autoencoder; data compression; image reconstruction; TensorFlow


VOPSON, Melvin M. The world’s data explained: How much we’re producing and where it’s all stored. In: World Economic Forum, May. 2021.

WELCH, Terry A. A technique for high- performance data compression. Computer, 1984, 17.06: 8-19.

WIGGINS, Richard H., et al. Image file formats: past, present, and future. Radiographics, 2001,

3: 789-798.

MAZIASHVILI, A. R. Feasibility of using neural networks for compression of video data. Information and control systems in railway transport,, 2016, 6: 30-35.


COURVILLE, Aaron. Deep learning. MIT press, 2016.


GIRYES, Raja. Autoencoders. arXiv preprint arXiv:2003.05991, 2020.

DERTAT, Arden. Applied deep learning - part 3: Autoencoders. Towards data science, 2017.

DUMOULIN, Vincent; VISIN, Francesco. A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285, 2016.

DONG, Chao, et al. Learning a deep convolutional network for image super- resolution. In: Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV.

Springer International Publishing, 2014. p. 184-199.


Roland. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.

KINGMA, Diederik P.; BA, Jimmy. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.



  • There are currently no refbacks.