Learn More
-For object recognition invariant to changes in the object's position, size, and in-plane rotation, higher-order neural networks (HONNs) have numerous advantages over other neural network approaches. Because distortion invariance can be built into the architecture of the network, HONNs need to be trained on just one view of each object, not numerous(More)
A higher-order neural network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous(More)
The authors describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096x4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten(More)
Here we study the optical phase errors introduced into an optical correlator by the input and filter plane magneto-optic spatial light modulators. We measure and characterize the magnitude of these phase errors, evaluate their effects on the correlation results, and present a means of correction by a design modification of the binary phase-only(More)
The authors demonstrate a second-order neural network that has learned to distinguish between two objects, regardless of their size or translational position, after being trained on only one view of each object. Using an image size of 16*16 pixels, the training took less than 1 min of run time on a Sun 3 workstation. A recognition accuracy of 100% was(More)
The optimality of correlation filters is an important issue in applications of pattern recognition. We consider here both binary phase-only filters (BPOFs) and amplitude encoded binary phase-only filters (AE BPOFs) and study the results of optimizing the filters for a real world object (the Space Shuttle). We find that while only small improvements result(More)
A modified binary synthetic discriminant function filter designed to recognize objects over a range of rotated views has been verified on a laboratory optical correlator. A binary synthetic discriminant function filter has been previously described that will produce a specified correlation response for a set of training images. [See D. A. Jared and D. J.(More)