Vector quantization and signal compression
Vector quantization and signal compression
Multilayer perceptrons for image data compression and speech recognition
Multilayer perceptrons for image data compression and speech recognition
Hi-index | 0.00 |
Performance of vector quantization for image compression can be improved by using a variable rate code which is able to designate more bits to regions of an image that are active or difficult to code, and fewer bits to less active regions. Two schemes are presented here for directly designing variable rate tree-structured vector quantizers by growing the tree one node at a time. One is to select the node with the largest average distortion within one node to split. The other is to split the node with the largest largest eigenvalue of the input covariance matrix. A comparision with a previously proposed scheme [5, 6] shows that the proposed schemes have better performance in terms of visual quality with reduced complexity.