Title :
A transputer-based self-tuning edge detection chain
Author :
Antola, Anna ; Scarabottolo, Nello ; Spertini, Massimo
Author_Institution :
Dept. of Electron., Politecnico di Milano, Italy
Abstract :
The article deals with the application of transputer-based parallel processing architectures to low level vision problems. In particular to verifying the feasibility of a high-performance edge detector capable of tuning its own behavior to the characteristics of each particular image, in order to maximize the quality of the results. A first, prototype of this edge detector has been completed. In this prototype, some widely known algorithms for edge detection have been parallelized and integrated to allow the edge detector to compare their performances on a given portion of the image to be processed, and to select the best suited algorithm
Keywords :
parallel architectures; parallel machines; pattern recognition; picture processing; detection algorithm efficiency; differential operators; edge detector; edge map; enhancement/thresholding; feasibility; low level vision; monochromatic images; self-tuning edge detection chain; template matching; transputer-based parallel processing architectures; Character recognition; Detectors; Image edge detection; Image processing; Image recognition; Noise level; Parallel processing; Pixel; Prototypes; Tuning;
Conference_Titel :
System Sciences, 1992. Proceedings of the Twenty-Fifth Hawaii International Conference on
Conference_Location :
Kauai, HI
Print_ISBN :
0-8186-2420-5
DOI :
10.1109/HICSS.1992.183175
