Automatic Target Recognition and Indexing by Non-Orthogonal Image Expansion and Data-Dependent Normalization with Implementation.
Final rept. 1 Aug 83-31 Jul 97,
ILLINOIS UNIV AT CHICAGO CIRCLE
Pagination or Media Count:
This research is concerned with the development of a neural system for robust projective-invariant recognition of multiple targets which may be partially occluded in a cluttered background based on single gray-level images. For this purpose we have developed in the research a new method for affine-invariant iconic representation and recognition of targets using a novel set of GaborFourier kernels with multi-dimensional indexing in the frequency domain. An affine-invariant representation of local image patches is extracted in the form of spectral signatures, by directly convolving the image with our novel configuration of these kernels. We achieved 100 correct recognition rates with a model library of 26 models over a wide range of viewing poses and distances 360 of rotation and tilt and 82 of slant and 4 octaves of scale. The system also maintains its 100 recognition rate in high levels of noiseclutter up to -17 dB and to resolution degradation 15 reduction. A novel method for representation and recognition of 3D ObjectTargets based on 3D frequency domain representation was also developed and tested.
- Target Direction, Range and Position Finding
- Radiofrequency Wave Propagation