Abstract
The notion of polygonal entropy is introduced which captures the degree of nonconvexity of a polygon through a measure of polygonal visibility. We show that the entropy of a simple polygon is maximal if and only if it is convex. When 'normalized' the entropy measure is a number between ε (a small positive nonzero number) and 1 providing a convenient index which represents the degree of irregularity (nonconvexity) of a simple polygon. A similar but less computationally burdensome measure is also proffered. Suggested uses of the measure are: the evaluation of computational complexity of vision algorithms, pattern recognition and architectural space planning.
Original language | English |
---|---|
Pages (from-to) | 229-235 |
Number of pages | 7 |
Journal | Pattern Recognition Letters |
Volume | 10 |
Issue number | 4 |
DOIs | |
State | Published - 1 Jan 1989 |
Keywords
- Polygon
- convexity measure
- degree of nonconvexity
- entropy
- nonconvex polygon
- visible polygon
- vision algorithms
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence