Title :
Encoding pyramids by Labeling RAAM
Author :
Lonardi, Stefano ; Sperduti, Alessandro ; Starita, Antonina
Author_Institution :
Dipartimento di Inf., Pisa Univ., Italy
Abstract :
In this paper we present preliminary results on the application of Labeling RAAM (LRAAM) for encoding pyramids. The LRAAM is a neural network able to develop reduced representations of labeled directed graphs. The capability of such representations to preserve structural similarities is demonstrated on a pyramid. We suggest to exploit this skill in data compression and/or to discover scale affine auto-similarities
Keywords :
backpropagation; data compression; directed graphs; image coding; neural nets; quadtrees; redundancy; Labeling RAAM; backpropagation; data compression; image coding; labeled directed graphs; neural network; pyramid encoding; quadtree; reduced representations; redundancy; scale affine auto-similarities; similar hidden representation; structural similarity; Data compression; Data structures; Electronic mail; Encoding; Image analysis; Image coding; Image resolution; Labeling; Neural networks; Pixel;
Conference_Titel :
Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop
Conference_Location :
Ermioni
Print_ISBN :
0-7803-2026-3
DOI :
10.1109/NNSP.1994.366000
