Shift-invariant recognition of rotationally deformed ship silhouettes at multiple resolution scales

A novel method for two-dimensional pattern recognition and feature extraction, applicable to microprocessor-based vision systems, is presented which employs fractal geometric analysis. Fractal contour transformation and transform correlation techniques are discussed in relation to their effectiveness in classifying rotationally deformed images over a wide resolution range. Fractal geometric analysis exhibits several attributes.

One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. This manuscript is an author version and may be cited as: Schmalz, M. S., & Caimi, F. M. (1986). Shift-invariant recognition of rotationally deformed ship silhouettes at multiple resolution scales. In D. P. Casasent & A. G. Tescher (Eds.), Hybrid image processing: April 1-2, 1986, Orlando, Florida. Proceedings of the SPIE, 638 (pp. 201-213). Bellingham, WA, USA.

Florida Atlantic University. Harbor Branch Oceanographic Institute contribution #504.