Neural nets for invariant object recognition

The authors introduce a new class of artificial neural network (ANN) models based on transformed domain feature extraction. Many optical and/or digital recognition systems based on transformed domain feature extraction are available in practice. Optical systems are inherently parallel in nature and are preferred for real time applications, whereas digital systems are more suitable for non-linear operations. In their ANN models the authors combine advantages of both digital and optical systems. Many transformed domain feature extraction techniques have been developed during the last three decades. They include: the Fourier transform (FT), the Walsh Hadamard transform (WHT), the discrete cosine transform (DCT), etc. As an example, the authors have developed ANN models using the FT and WHT domain features. The models consist of two stages, the feature extraction stage and the recognition stage. The authors use back-propagation and competitive learning algorithms in the recognition stage. They use these ANN models for invariant object recognition. The models have been used successfully to recognize various types of aircraft, and also have been tested with test patterns