We propose a new set of rotationally and translationally invariant features for image or pattern recognition and classification. The new features are cubic polynomials in the pix...
Adaptation of the spike-frequency response to constant stimulation, as observed on various timescales in many neurons, reflects high-pass filter properties of a neuron's tran...
Abstract. Fractal image compression is an engaging and worthwhile technology that may be successfully applied to still image coding, especially at high compression ratios. Unfortun...
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...
This paper argues that specified blocks have every advantage over the combination of assertions, preconditions, postconditions, invariants, and variants, both for verifying program...