RT Journal Article
T1 A Convolutional Autoencoder and a Neural Gas model based on Bregman Divergences for Hierarchical Color Quantization
A1 Fernández-Rodríguez, Jose David
A1 Palomo-Ferrer, Esteban José
A1 Benito-Picazo, Jesús
A1 Domínguez-Merino, Enrique
A1 López-Rubio, Ezequiel
A1 Ortega-Zamorano, Francisco
K1 Procesado de imágenes - Técnicas digitales
K1 Color
AB 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.
PB Elsevier
YR 2023
FD 2023
LK https://hdl.handle.net/10630/36529
UL https://hdl.handle.net/10630/36529
LA eng
NO José David Fernández-Rodríguez, Esteban J. Palomo, Jesús Benito-Picazo, Enrique Domínguez, Ezequiel López-Rubio, Francisco Ortega-Zamorano, A convolutional autoencoder and a neural gas model based on Bregman divergences for hierarchical color quantization, Neurocomputing, Volume 544, 2023, 126288, ISSN 0925-2312, https://doi.org/10.1016/j.neucom.2023.126288. (https://www.sciencedirect.com/science/article/pii/S0925231223004113)
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 1 mar 2026