Study of two neural feed-forward structures for digital image compression


  • Andres Eduardo Gaona-Barrera Universidad Distrital Francisco José de Caldas.
  • Néstor Andrés Lugo-Currea Universidad Distrital Francisco José de Caldas.
  • Álvaro Fernando Roldán-Hernández Universidad Distrital Francisco José de Caldas.


compression rate, digital image compression, lossy compression, feedforward neuronal networs, peak signal noise relation


This document shows and explains the process for compressing images, in grayscale and in color, using two neural topologies: image function and funnel. For the analysis of neuronal schemes, the number of neurons and layers, type of image, size and number of blocks during training are considered; in order to give experimental support to neural architectures. Quality criteria of the image obtained are also analyzed, such as peak signal-to-noise ratio (PSNR) and compression rate. The importance of the selection of parameters evaluated in quality and compression time is evident. The experimentation process shows that the funnel-type architecture allows to achieve values ​​higher than 35dB in terms of PSNR and 2 bits per pixel in gray images or 3 bpp in color images, with times less than 3 seconds for images smaller than 1 mega pixel. Finally, some recommendations are made based on the methodology used when it is desired to understand images with feed-through networks around the selection of architecture parameters, the pre-processing of the image and the training of the network.

= 28 veces | PDF (ESPAÑOL (ESPAÑA))
= 32 veces|


Download data is not yet available.


Tecnología de los contenidos multimedia. Edición y compresión de imágenes estáticas. Programa oficial de postgrado: Master en comunicaciones, redes y gestión de contenidos. España. Disponible en: Diciembre 2008.

R. Ferzli, M. Adnan. Subsampling image compression using Al-Aloui backpropagation algorithm. Electronics, Circuits and Systems. 14th IEEE International Conference. Arizona. 2007. pp. 1260-1263.

W. Gillespie. Still image compression using neural networks. Utah University. Logan. UT. 2005.

V. Rama, P. Vaddella, K. Rama. “Artificial neural networks for compression of digital imágenes: a review”. International Journal of Reviews in Computing. Vol 10. 2010. pp. 75-82

D. Alvarez, M. Guevara, G. Holguin. Preprocesamiento de imágnes aplicadas a mamografías digitales. Universidad tecnológica de Pereira. Scientia et Technica Año XII. No 31. Pereira. Colombia. 2006. pp. 1-6.

A. Durai, E. Saro. “Image Compression with Back- Propagation Neural Network Using Cumulative Distribution Function”. World Academy of Science, Engineering and Tech. Vol. 17. 2006. pp. 60-64.

S. Basu, K. Kayal, J. Sil. Edge preserving image compression technique using adptative feed forward neural network. Proceedings of the ninth IASTED International Conference INTERNET AND MULTIMEDIA SYSTEMS AND APPLICATION. Switzerland. 2005. pp. 467-471.

H. Sahoolizadeh, A. Suratgar. Adaptative image compression using neural networks. Setit, 5th International Conference: Sciences of Electronics Technologies of Information and Telecommunications. Tunisia. 2009. pp. 1-5.

I. Vilovic. An experience in image compression using neural networks. 48th International Symposium ELMAR Focused on Multimedia Signal Processing, Zadar Croatia. 2006. pp. 95-98.

Signal and image processing institute. Ming Hsieh Department of Electrical Engineering. University of southern. California. Disponible en: Consultado en Noviembre de 2011.

N. Lugo, F. Roldan. “Imágenes usadas en la compresión de imágenes con redes neuronales”. Disponible en:ágenes_usadas_en_la_compresión_de_imágenes_con_ redes_neuronales.rar. Publicado en Enero de 2012 y consultado Marzo de 2012.



How to Cite

Gaona-Barrera, A. E., Lugo-Currea, N. A., & Roldán-Hernández, Álvaro F. (2013). Study of two neural feed-forward structures for digital image compression. Revista Facultad De Ingeniería Universidad De Antioquia, (65), 85–98. Retrieved from