Straight-line detection on a gated-connection VLSI network

Shu, D.B.; Nash, J.G.; Eshaghian, M.M.; Kim, K.

doi:10.1109/icpr.1990.119400

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interested readers can find a detailed description of minimumfinding on GCN in [9]. Each connected component can compute the minimum index in O(1og n) time concurrently.…”

Section: Methodsmentioning

confidence: 99%

“…in [9]. In [9], the size of the processor array matches the size of the input image. In reallife situations, the size of the image can be much larger than the size of the PE array.…”

Section: Partitioned Line Detectionmentioning

confidence: 97%

“…Since only a portion of a line is detected at a time, the line portion information should be stored and used in detecting the rest of the line. We use the same coarse line detection algorithm used in [9] for processing each subimage. After each subimage is processed, the information needed for line detection in adjacent subimages are stored in the memory.…”

Section: Partitioned Line Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Parallel implementation of image understanding tasks on gated-connection networks

Shu

Nash

Kim³

[1991] Proceedings. The Fifth International Parallel Processing Symposium

Self Cite

View full text Add to dashboard Cite

In this paper, we preaent a summary of our reaearch in deign and implementation of parallel algorithms for image computing tasks on an enhanced mesh connected computer called Gated-Connection Network (GCN). The GCN allows dynamic reconfiguration of mesh interconnectivity using switches located at the grid pointa. The flexibility of the GCN leads to significant improvements in time complexity of several image computing tasks. Line detection and finding connected components are some of the problema studied for low and intermediate level processing. Parallel implementation of symbolic computation tasks for image understanding and pattern recognition is another claw of problems addressed in this paper.

show abstract

“…Interested readers can find a detailed description of minimumfinding on GCN in [9]. Each connected component can compute the minimum index in O(1og n) time concurrently.…”

Section: Methodsmentioning

confidence: 99%

“…in [9]. In [9], the size of the processor array matches the size of the input image. In reallife situations, the size of the image can be much larger than the size of the PE array.…”

Section: Partitioned Line Detectionmentioning

confidence: 97%

Section: Partitioned Line Detectionmentioning

confidence: 99%

See 1 more Smart Citation