research-article

A convolutional autoencoder and a neural gas model based on Bregman divergences for hierarchical color quantization

Authors:

José David Fernández-Rodríguez,

Esteban J. Palomo,

Jesús Benito-Picazo,

Enrique Domínguez,

Ezequiel López-Rubio,

Francisco Ortega-ZamoranoAuthors Info & Claims

Volume 544, Issue C

https://doi.org/10.1016/j.neucom.2023.126288

Published: 01 August 2023 Publication History

Highlights

•

We present a novel hybrid model composed of a convolutional autoencoder and a Growing Hierarchical Bregman Neural Gas (GHBNG) for hierarchical color quantization.

•

The performance of our proposed hybrid model attains better compressed sizes than the autoencoder alone.

•

In the cases that autoencoders alone yield about the same compression ratio, our hybrid model attains a better compressed image quality as measured by the PSNR and SSIM performance metrics.

•

Our proposal learns a reduced representation of an input image with a tunable compression strength given by the number of convolutional layers of the encoder section of the autoencoder (N parameter).

•

GHBNG gets better compression ratios when compared with other hierarchical selforganizing models.

Abstract

Color quantization (CQ) is one of the most common and important procedures to be performed on digital images. In this paper, a new approach to hierarchical color quantization is described, presenting a novel neural network architecture integrated by a convolutional autoencoder and a Growing Hierarchical Bregman Neural Gas (GHBNG). GHBNG is a CQ algorithm that allows the compression of an image by choosing a reduced set of the most representative colors to generate a high-quality reproduction of the original image. In the technique proposed here, an autoencoder is used to translate the image into a latent representation with higher per-pixel dimensionality but reduced resolution, and GHBNG is then used to quantize it. Experimental results confirm the performance of this technique and its suitability for tasks related to color quantization.

References

[1]

Y. Linde, A. Buzo, R. Gray, An algorithm for vector quantizer design, IEEE Trans. Commun. 28 (1) (1980) 84–95.

[2]

J.C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algoritms, Plenum Press, 1981.

[3]

J. Hertz, A. Krogh, R. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.

[4]

T. Kohonen, The self-organizing map, Proc. IEEE 78 (9) (1990) 1464–1480.

[5]

T. Kohonen, Self-organized formation of topologically correct feature maps, Biol. Cybern. 43 (1) (1982) 59–69.

[6]

E. López-Rubio, Probabilistic self-organizing maps for continuous data, IEEE Trans. Neural Networks 21 (10) (2010) 1543–1554.

[7]

E. López-Rubio, Probabilistic self-organizing maps for qualitative data, Neural Networks 23 (10) (2010) 1208–1225.

[8]

E. López-Rubio, E.J. Palomo-Ferrer, J.M. Ortiz-de Lazcano-Lobato, M.C. Vargas-González, Dynamic topology learning with the probabilistic self-organizing graph, Neurocomputing 74 (16) (2011) 2633–2648.

[9]

T. Kohonen, Essentials of the self-organizing map, Neural Networks 37 (2013) 52–65.

Digital Library

[10]

E. López-Rubio, E. Palomo-Ferrer, Growing hierarchical probabilistic self-organizing graphs, IEEE Trans. Neural Networks 22 (7) (2011) 997–1008.

[11]

E.J. Palomo, J. Benito-Picazo, E. López-Rubio, E. Domínguez, Unsupervised color quantization with the growing neural forest, in: I. Rojas, G. Joya, A. Catala (Eds.), Advances in Computational Intelligence, Springer International Publishing, Cham, 2017, pp. 306–316.

[12]

A. Rauber, D. Merkl, M. Dittenbach, The growing hierarchical self-organizing map: Exploratory analysis of high-dimensional data, IEEE Trans. Neural Networks 13 (6) (2002) 1331–1341.

[13]

B. Fritzke, A growing neural gas network learns topologies, Advances in Neural Information Processing Systems 7 (1995) 625–632.

[14]

E.J. Palomo, E. López-Rubio, The growing hierarchical neural gas self-organizing neural network, IEEE Trans. Neural Networks Learn. Syst. 28 (9) (2017) 2000–2009.

[15]

E.J. Palomo, M.A. Molina-Cabello, E. López-Rubio, R.M. Luque-Baena, A new self-organizing neural gas model based on Bregman divergences, in: 2018 International Joint Conference on Neural Networks (IJCNN) (2018) 1–8.

[16]

E.J. Palomo, J. Benito-Picazo, E. Domínguez, E. López-Rubio, F. Ortega-Zamorano, Hierarchical color quantization with a neural gas model based on bregman divergences, Adv. Intell. Syst. Comput. 1401 (2022) 327–337.

[17]

A. Banerjee, S. Merugu, I.S. Dhillon, J. Ghosh, Clustering with Bregman divergences, J. Mach. Learn. Res. 6 (2005) 1705–1749.

[18]

E.J. Palomo, E. Domínguez, Hierarchical color quantization based on self-organization, J. Math. Imaging Vision 49 (1) (2013) 1–19.

Digital Library

[19]

L. Zhou, C. Cai, Y. Gao, S. Su, J. Wu, Variational autoencoder for low bit-rate image compression, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2617–2620.

[20]

P. Vincent, H. Larochelle, Y. Bengio, P.-A. Manzagol, Extracting and composing robust features with denoising autoencoders, in: Proceedings of the 25th International Conference on Machine Learning, Association for Computing Machinery, New York, NY, USA, 2008, p. 1096–1103.

[21]

Z. Cheng, H. Sun, M. Takeuchi, J. Katto, Deep convolutional autoencoder-based lossy image compression, 2018 Picture Coding Symposium (PCS) (2018) 253–257.

[22]

Z. Cheng, H. Sun, M. Takeuchi, J. Katto, Energy compaction-based image compression using convolutional autoencoder, IEEE Trans. Multimedia 22 (4) (2020) 860–873.

Digital Library

[23]

M.D. Zeiler, D. Krishnan, G.W. Taylor, R. Fergus, Deconvolutional networks, in: 2010 IEEE Computer Society Conference on computer vision and pattern recognition, IEEE, 2010, pp. 2528–2535.

[24]

L. Bregman, The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming, USSR Comput. Math. Math. Phys. 7 (3) (1967) 200–217.

[25]

Y. Censor, S. Zenios, Parallel Optimization: Theory, Algorithms, and Applications, Oxford University Press, 1998.

[26]

T. Villmann, S. Haase, Divergence-based vector quantization, Neural Comput. 23 (2011) 1343–1392.

[27]

E. Jang, C. Fyfe, H. Ko, Bregman divergences and the self organising map, Lect. Notes Comput. Sci. 5326 (2008) 452–458.

[28]

J. Liu, D. Liu, W. Yang, S. Xia, X. Zhang, Y. Dai, A comprehensive benchmark for single image compression artifact reduction, IEEE Trans. Image Process. 29 (2020) 7845–7860.

[29]

P. Heckbert, Color image quantization for frame buffer display, ACM Siggraph Comput. Graphics 16 (3) (1982) 297–307.

[30]

Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: From error visibility to structural similarity, IEEE Trans. Image Process. 13 (4) (2004) 600–612.

Digital Library

[31]

S.P. Chokkalingam, K. Komathy, M. Vinoth, R. Saravanan, Performance analysis of bone images using various edge detection algorithms and denoising filters, Int. J. Pharma Bio Sci. 5 (2) (2014) B943–B954.

Recommendations

DWT-based scene-adaptive color quantization
Special issue on multi-dimensional image processing

Color quantization is the process of reducing the number of colors in an image. That is, color quantization maps a large number of colors into a much smaller number of representative colors while keeping color distortion to an acceptable level. The ...
An efficient color quantization based on generic roughness measure

Color quantization is a process to compress image color space while minimizing visual distortion. The quantization based on preclustering has low computational complexity but cannot guarantee quantization precision. The quantization based on ...
Hierarchical Color Quantization Based on Self-organization

In this paper, a new hierarchical color quantization method based on self-organizing maps that provides different levels of quantization is presented. Color quantization (CQ) is a typical image processing task, which consists of selecting a small number ...

Comments

Information & Contributors

Information

Published In

cover image Neurocomputing

Neurocomputing Volume 544, Issue C

Aug 2023

300 pages

ISSN:0925-2312

Issue’s Table of Contents

Elsevier B.V.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 August 2023

Author Tags

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Nov 2024

Other Metrics

View Author Metrics

Citations

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents