0000000000080989

AUTHOR

Di Gesù V.

showing 6 related works from this author

PICTORIAL-C LANGUAGE FOR THE HERMIA-MACHINE

1992

The design and implementation of algorithms on multi-processors machines is hard. The paper describes the general features of the Pictorial C Language (PICL) that is oriented to image analysis. Its integration in the software environment of the HERMIA machine, and the handling of the related interconnecting network topology is also given.

Language Pictorial Language Icon Language reconfigurable machine.Settore INF/01 - Informatica
researchProduct

HERMIA - GENERAL DESCRIPTION

1992

Settore INF/01 - InformaticaReconfigurable Architecture Hermia Transputer Filtering Feature extraction classification.
researchProduct

Pictorial information retrieval with uncertain knowledge

1990

In the paper an integrated pictorial database is described. The design of the data management requires many efforts to preserve consistency and integrity. The retrieval operations are designed to support a uniform view of heterogeneous information including uncertain ones; in this last case, non-standard techniques have to be developed. Applications to astronomical images and an outline of the implementation status are given.

Settore INF/01 - InformaticaPictorial Information hierarchical architecture numerical description Pictorial DB
researchProduct

HERMIA: An Heterogeneous and Reconfigurable Machine for Image Analysis

1990

In this paper is described the general architecture of an Heterogeneous and Reconfigurable Machine for Image Analysis (HERMIA); the first prototype of the system has been developed at the University of Palermo. Conventional hardware has been used in order to emulate the machine and evaluate the system performance Preliminary results are presented and discussed.

Settore INF/01 - InformaticaHERMIA-machine INMOS BOO9 FFT algorithm Programming language.
researchProduct

An Integrated Method for Image Retrieval

1995

This paper presents an information fusion method for image retrieval; the retrieval strategy is based on statistical and geometrical features extracted from sub-images. Our goal is to find a set of best similar images related to a prototype image; this goal may be obtained according to image content rather than symbolic attributes. MRI (Magnetic Resonance Imaging) images and astronomical images have been adopted to test the method. Main steps of the procedure to retrieve images are: (l) Segmentation, (2) Matching, and (3) Decision. The first step involves four clusters co-operating segmentation algorithms; in the matching step, a sets of candidate similar images is provided; finally an info…

pictorial darabase feature extraction image segmentation information fusion.Settore INF/01 - Informatica
researchProduct

Human and Machine Perception 2 - Emergence, Attention, and Creativity

1999

Emergence attention creativity evolution cooperating system data mining.
researchProduct