A robust neural network based object recognition system and its SIMD implementation

Recognition of objects is a particularly demanding problem, if one considers that each image must be interpreted in milliseconds (usually 30 or 40 frames/second). In this paper we propose a massively parallel object recognition system, which makes use of the multi polygonal approximation scheme for the extraction of rotation and translation invariant shape features, in connection with artificial neural networks for the parallel classification of the extracted features. The system has been successfully applied for recognizing aircraft shapes in different sizes, orientations, with the addition of noise distortion and occlusion. Timings on the Connection Machine 200 are also reported.