Rotation Invariant Pattern Recognition

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.

[1]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[2]  J. Mendelsohn,et al.  Digital Methods In The Design Of Optical Matched Filters For Target Recognition , 1980, Photonics West - Lasers and Applications in Science and Engineering.

[3]  K G Leib,et al.  Aerial reconnaissance film screening using optical matched-filter image-correlator technology. , 1978, Applied optics.

[4]  D Casasent,et al.  Polar camera for space-variant pattern recognition. , 1978, Applied optics.

[5]  H H Arsenault,et al.  Incoherent method for rotation-invariant recognition. , 1982, Applied optics.

[6]  A. Cormack.  Representation of a Function by Its Line Integrals, with Some Radiological Applications , 1963 .

[7]  James R. Leger,et al.  IMAGE CLASSIFICATION BY AN OPTICAL IMPLEMENTATION OF THE FUKUNAGA-KOONTZ TRANSFORM. , 1982 .

[8]  T. Peli.  An algorithm for recognition and localization of rotated and scaled objects , 1981, Proceedings of the IEEE.

[9]  Yoshihiro Ohtsuka,et al.  Rotational filtering for randomly oriented pattern recognition , 1981 .

[10]  King-Sun Fu,et al.  Shape Discrimination Using Fourier Descriptors , 1977, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  H. Caulfield,et al.  Computer recognition of 2-D patterns using generalized matched filters. , 1982, Applied optics.

[12]  H H Arsenault,et al.  Digital multiple correlation for pattern recognition. , 1982, Applied optics.

[13]  S P Almeida,et al.  Rotational matched spatial filter for biological pattern recognition. , 1980, Applied optics.

[14]  D Casasent,et al.  Deformation invariant optical processors using coordinate transformations. , 1977, Applied optics.

[15]  A Iwamoto,et al.  Rotation-, shift-, and magnification-insensitive periodic-pattern-defects optical detection system. , 1980, Applied optics.