Share Email Print

Proceedings Paper

Vectorization method based on energy minimization principle
Author(s): Naoya Tanaka; Takeshi Kamimura
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Vectorizing the skeleton of a binary digital image is important for recognizing drawings and maps. A new vectorization method, based on the energy minimization principle, is proposed in this paper. The method involves thinning, line segment approximation, and geometric transformation. The skeleton line, obtained after the line segment approximation process, includes shape distortion caused by thinning. In the geometric transformation process, the line segments are shifted for minimizing the value, defined in the neighbor of each corner, junction, and so on, by the smoothness and the difference between line segments and skeleton of an original image. The proposed method has an advantage of reducing the various kinds of distortions, compared with the conventional methods.

Paper Details

Date Published: 9 April 1993
PDF: 10 pages
Proc. SPIE 1832, Vision Geometry, (9 April 1993); doi: 10.1117/12.142168
Show Author Affiliations
Naoya Tanaka, NEC Corp. (Japan)
Takeshi Kamimura, NEC Corp. (Japan)

Published in SPIE Proceedings Vol. 1832:
Vision Geometry
Robert A. Melter; Angela Y. Wu, Editor(s)

© SPIE. Terms of Use
Back to Top