Neuron network for low-level vision: texture segmentation

An approach to low-level-vision neural net modeling which is based on the works of N.V. Pozin et al. (1978) on simulation of peripheral neuron structures in the auditory and visual system is proposed. The four-layered neural net described has two modes of processing: texture segmentation of images of visual scenes and extraction of texture boundaries of the images. The efficiency of the neural net was confirmed by computer simulation. The proposed network corresponds to the lateral geniculate nucleus (LGN) level of the visual system.<
>