Title :
Neuron network for low-level vision: texture segmentation
Author_Institution :
Dept. of Ergonomics & Inf. Process. Syst., MATI, Moscow, Russia
Abstract :
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
Keywords :
computer vision; image segmentation; image texture; neural nets; computer simulation; efficiency; four-layered neural net; lateral geniculate nucleus; low-level-vision neural net modeling; peripheral neuron structures; texture boundaries; texture segmentation; visual scenes; Computational modeling; Computer simulation; Ergonomics; Image processing; Image segmentation; Information processing; Layout; Neural networks; Neurons; Visual system;
Conference_Titel :
Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on
Conference_Location :
Rostov-on-Don
Print_ISBN :
0-7803-0809-3
DOI :
10.1109/RNNS.1992.268522
