17 March 1983 Rotation Invariant Pattern Recognition
Author Affiliations +
Conventional matched filtering is sensitive to rotation of the object to be detected. If the target object is rotated, the signal to noise ratio of the output correlation is reduced with the result that the object may not be detected. Efforts have been made towards developing matched filters with signal to noise ratios that are space invariant and rotation invariant with respect to the target. Our latest approach has been to extract from the target some circular harmonic component, and to use a filter matched to this component. A complete digital simulation using simple two-dimensional objects has resulted in the successful detection of rotated target objects in a field of different objects. The same technique has also been implemented in an optical processor using computer generated holograms. To discriminate between objects that are almost similar, a pseudo-object is used to generate the matched filter.
© (1983) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H. H. Arsenault, H. H. Arsenault, Y. N. Hsu, Y. N. Hsu, K. Chalasinska-Macukow, K. Chalasinska-Macukow, Y. Yang, Y. Yang, } "Rotation Invariant Pattern Recognition", Proc. SPIE 0359, Applications of Digital Image Processing IV, (17 March 1983); doi: 10.1117/12.965974; https://doi.org/10.1117/12.965974

Back to Top