- Full text PDF available (1)
- This year (0)
- Last five years (0)
High-quality image compression algorithms are capable of achieving transmission or storage rates of 0.3 to 0.5 b/pixel with low degradation in image quality. In order to obtain even lower bit rates, we relax the usual RMS error definition of image quality and allow certain "less critical" portions of the image to be transmitted as texture models. These… (More)
The resonance correlation network (RCN) is a parallel continuous-time unsupervised pattern categorization machine than can operate on binary or continuous-valued data. The architecture is motivated by adaptive resonance theory (ART). Simple modifications, however, eliminate the problems associated with learning patterns presented for arbitrary time… (More)
The property inheritance network (PIN) is a dynamically controlled machine that accesses information stored in a hierarchical content addressable memory. The associative memory is implemented using adaptive resonance circuits. These circuits are monitored by a set of control neurons that become active when certain system states occur and generate signals… (More)
A general procedure is introduced for sidelobe and noise reduction in optical or digital signal processing. Specific examples of sidelobe reduction in imaging are presented. It is demonstrated that the new method provides superior spatial resolution to previously proposed sidelobe-reduction techniques.
The problem of reconstructing digital data with nonideal analog interpolators is addressed. A theoretical viewpoint is taken which specifies optimal data reconstructors when a predisplay digital filter is employed. This theory allows for a weighted error definition so that solutions with different desired qualities may be obtained. Results for… (More)