Image compression by vector quantization with recurrent discrete networks

Authors:
Domingo López-Rodríguez;Enrique Mérida-Casermeiro;Juan M. Ortiz-de-Lazcano-Lobato;Ezequiel López-rubio
Affiliations:
Department of Applied Mathematics, University of Málaga, Málaga, Spain;Department of Applied Mathematics, University of Málaga, Málaga, Spain;Department of Computer Science and Artificial Intelligence, University of Málaga, Málaga, Spain;Department of Computer Science and Artificial Intelligence, University of Málaga, Málaga, Spain
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 12
Cited 4

Competitive learning algorithms for vector quantization

Neural Networks
A new competitive learning approach based on an equidistortion principle for designing optimal vector quantizers

Neural Networks
Robust image association by recurrent neural subnetworks

Neural Processing Letters
A new family of multivalued networks

Neural Networks
Expansive and Competitive Learning for Vector Quantization

Neural Processing Letters
A Recurrent Multivalued Neural Network for the N-Queens Problem

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Connectionist Models of Neurons, Learning Processes and Artificial Intelligence-Part I
Nonlinear vector prediction using feed-forward neural networks

IEEE Transactions on Image Processing
A modular neural network vector predictor for predictive image coding

IEEE Transactions on Image Processing
Use of nonlinear principal component analysis and vector quantization for image coding

IEEE Transactions on Image Processing
Optimally adaptive transform coding

IEEE Transactions on Image Processing
Adaptive combination of PCA and VQ networks

IEEE Transactions on Neural Networks
Image compression by self-organized Kohonen map

IEEE Transactions on Neural Networks

Stochastic Functional Annealing as Optimization Technique: Application to the Traveling Salesman Problem with Recurrent Networks

KI '07 Proceedings of the 30th annual German conference on Advances in Artificial Intelligence
Two pages graph layout via recurrent multivalued neural networks

IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
K-pages graph drawing with multivalued neural networks

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Shortest common superstring problem with discrete neural networks

ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we propose a recurrent multivalued network, generalizing Hopfield's model, which can be interpreted as a vector quantifier. We explain the model and establish a relation between vector quantization and sum-of-squares clustering. To test the efficiency of this model as vector quantifier, we apply this new technique to image compression. Two well-known images are used as benchmark, allowing us to compare our model to standard competitive learning. In our simulations, our new technique clearly outperforms the classical algorithm for vector quantization, achieving not only a better distortion rate, but even reducing drastically the computational time.