1987
DOI: 10.1016/0734-189x(87)90124-1
|View full text |Cite
|
Sign up to set email alerts
|

Rough approximation of shapes in pattern recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
7
0

Year Published

1991
1991
1991
1991

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(7 citation statements)
references
References 0 publications
0
7
0
Order By: Relevance
“…The least information becomes representation of the most regular shapes derived from the picture and assumes the names for the shapes. The least information must be on the symbolic level, because only symbolic information is independent of possible orientations of the pattern in the field of observation [24,26]. The symbolic representations of features is shown to be invariant in the space of observation.…”
Section: Involving Forks and Junctionsmentioning
confidence: 99%
See 1 more Smart Citation
“…The least information becomes representation of the most regular shapes derived from the picture and assumes the names for the shapes. The least information must be on the symbolic level, because only symbolic information is independent of possible orientations of the pattern in the field of observation [24,26]. The symbolic representations of features is shown to be invariant in the space of observation.…”
Section: Involving Forks and Junctionsmentioning
confidence: 99%
“…The up-to-date experience with the sequential implementation of the shape detection method [24][25][26] prove the following: there is much less ambiguity in interpretation of elementary and complex features, when compared with template matching. The method is resistant to variable thickness and discontinuities of edges.…”
Section: Involving Forks and Junctionsmentioning
confidence: 99%
“…The received feature approximation is merged by the requestor. where s is a merging operation, f is a feature approximation [16], a is a requested approximation of merged features (quantitative A or qualitative A), and 1 is the Parallel recognition of shapes with convexities and concavities requires a more sophisticated processing. Termination conditions for paralel shape coding is helpful for appropriate control o f execution of programs by nodes (e.g., t o know, when the entire object shape is coded by several nodes executing in parallel).…”
Section: Introductionmentioning
confidence: 99%
“…In our method, a rough set (composed of elements consisting o f feature names with attached attributes and parameters) [16] is broadcast t o fixed-address PES. The receivers identify more complex features, based on feature adjacency, expectations and constraints (Figs 1 -3).…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation