POSITION-INVARIANT, ROTATION-INVARIANT, AND SCALE-INVARIANT PROCESS FOR BINARY IMAGE RECOGNITION

A novel recognition process is presented that is invariant under posit ion, rotation, and scale changes. The recognition process is based on the Fang-Hausler transform [Appl. Opt. 29, 704 (1990)] and is applied to the autoconvolved image, rather than to the image itself. This make s the recognition process sensitive not only to the image histogram bu t also to its detailed pattern, resulting in a more reliable process t hat is also applicable to binary images. The proposed recognition proc ess is demonstrated, by use of a fast algorithm, on several types of b inary images with a real transform kernel, which contains amplitude, a s well as phase, information. Good recognition is achieved for both sy nthetic and scanned images. In addition, it is shown that the Fang-Hau sler transform is also invariant under a general affine transformation of the spatial coordinates. (C) 1997 Optical Society of America.