Show simple item record

Video Sequence Compression via Supervised Training on Cellular Neural Networks

dc.contributor.authorBerzal, José Andrés
dc.contributor.authorZufiria, Pedro
dc.contributor.authorRodriguez, Luis
dc.identifier.citationVideo Sequence Compression via Supervised Training on Cellular Neural Networks Luis Rodríguez (), Pedro J. Zufiria (), and J. Andrés Berzal () International Journal of Neural Systems 1997 08:01, 127-135es
dc.descriptionUtilización de la Red Neuronal Celular para la compresión de video.Supone uno de los primero algoritmos de Inteligencia Artificial y su aplicación a la compresión de
dc.description.abstractIn this paper, a novel approach for video sequence compression using Cellular Neural Networks (CNN's) is presented. CNN's are nets characterized by local interconnections between neurons (usually called cells), and can be modeled as dynamical systems. From among many different types, a CNN model operating in discrete-time (DT-CNN) has been chosen, its parameters being defined so that they are shared among all the cells in the network. The compression process proposed in this work is based on the possibility of replicating a given video sequence as a trajectory generated by the DT-CNN. In order for the CNN to follow a prescribed trajectory, a supervised training algorithm is implemented. Compression is achieved due to the fact that all the information contained in the sequence can be stored into a small number of parameters and initial conditions once training is stopped. Different improvements upon the basic formulation are analyzed and issues such as feasibility and complexity of the compression problem are also addressed. Finally, some examples with real video sequences illustrate the applicability of the
dc.publisherIos Presses
dc.subjectCellular Neural Networkses
dc.subjectDynamical systemes
dc.subjectVideo sequencyes
dc.subjectArtificial intelligencees
dc.titleVideo Sequence Compression via Supervised Training on Cellular Neural Networkses

Files in this item

This item appears in the following Collection(s)

Show simple item record

Los ítems de digital-BURJC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario