Desirable properties of robotics vision database systems are given, and structures which possess properties appropriate for some aspects of such database systems are examined. Included in the structures discussed is a family of networks in which link membership is determined by measures of proximity between pairs of the entities stored in the database. This type of network is shown to have properties which guarantee that the search for a matching feature vector is monotonic. That is, the database can be searched with no backtracking, if there is a feature vector in the database which matches the feature vector of the external entity which is to be identified. The construction of the database is discussed, and the search procedure is presented. A section on the support provided by the database for description of the decision-making processes and the search path is also included.
[1]
Hermann A. Maurer,et al.
Efficient worst-case data structures for range searching
,
1978,
Acta Informatica.
[2]
Godfried T. Toussaint,et al.
The relative neighbourhood graph of a finite planar set
,
1980,
Pattern Recognit..
[3]
Richard J. Lipton,et al.
Multidimensional Searching Problems
,
1976,
SIAM J. Comput..
[4]
David H. Krantz,et al.
The dimensional representation and the metric structure of similarity data
,
1970
.
[5]
Jon Louis Bentley,et al.
Data Structures for Range Searching
,
1979,
CSUR.
[6]
Olli Nevalainen,et al.
Computing relative neighbourhood graphs in the plane
,
1986,
Pattern Recognit..