Similarity-driven pictorial database design using entity-relationship approach

The entity-relationship approach is applied to similarity-driven pictorial database design. The capabilities and the limitations of computers are pres ented Advantages of the entity-relationship approach, and similarity-driven pictorial database design ar also presented. Classification of pictures, s imilarity-driven face databases, chromosome databases, leukocyte databases are investigated. Quantitative measure of equal-perimeter circular shape, e qual-area circular shape, elongated, spiculed, indented, slightly indented, and deeply indented leukocytes are also investigated. The entity-relations hip diagrams of a house, a house wit high roof,and a church are shown as il lustrative examples of this approach. the class of elongated isosceles tria ngles is viewed as a "fuzzy entity". Topics for future research are also st ates. The results have useful applications in data engineering, knowledge e ngineering, pattern recognition, artificial intelligence, fuzzy language th eory computer graphics, expert systems and pictorial database design.