Title | ||
---|---|---|
A parallel algorithm for determining two-dimensional object positions using incomplete information about their boundaries |
Abstract | ||
---|---|---|
Extraction of two-dimensional object locations using current techniques is a computationally intensive process. In this paper a parallel algorithm is presented that can specify the location of objects from edge streaks produced by an edge operator. Best-first searches are carried out in a number of non-interacting and localized edge streak spaces. The outcome of each search is a hypothesis. Each edge streak votes for a single hypothesis; it may also take part in the formation of other hypotheses. A poll of the votes determined the stronger hypotheses. The algorithm can be used as a front end to a visual pattern recognition system where features are extracted from the hypothesized object boundary or from the area localized by the hypothesized boundary. Experimental results from a biomedical domain are presented. |
Year | DOI | Venue |
---|---|---|
1989 | 10.1016/0031-3203(89)90034-4 | Pattern Recognition |
Keywords | Field | DocType |
parallel algorithm,automated histopathology,two-dimensional object recognition,two-dimensional object position,search,computer vision,incomplete information,feature-learning,edge-linking,model-based recognition,computer science,engineering,feature learning | Front and back ends,Computer science,Streak,Operator (computer programming),Artificial intelligence,Complete information,Computer vision,3D single-object recognition,Pattern recognition,Parallel algorithm,Feature learning,Machine learning,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
22 | 1 | Pattern Recognition |
Citations | PageRank | References |
5 | 0.90 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amir A. Amini | 1 | 443 | 63.30 |
Terry E. Weymouth | 2 | 439 | 125.44 |
David Anderson | 3 | 189 | 79.84 |