Abstract
In many image processing applications, it is desirable to combine partially overlapping images into one larger scene. We introduce a supervised correlation filter method that automatically detects overlapping image pairs and estimates proper alignment. We use on-line composite filter design to achieve rotation- and overlap-invariant image pairing. We present stochastic system analysis that provides closed-form expressions that predict correlation plane response distribution, defines an overlap-invariant filter bank architecture, and obtains the optimum training set size. The resulting high-level image processing method is numerically efficient, suited for optoelectronic implementation, and competitive with manual reconstruction in speed and accuracy.
© 1999 Optical Society of America
Full Article | PDF ArticleMore Like This
Wei Su and Laurence G. Hassebrook
Appl. Opt. 45(31) 8083-8091 (2006)
Bahram Javidi and Nasser Towghi
J. Opt. Soc. Am. A 16(9) 2146-2150 (1999)
Ping Zi-Liang and Erik Dalsgaard
Appl. Opt. 34(32) 7527-7531 (1995)