作者: A.P. Dhawan , T. Dufresne
DOI: 10.1109/IJCNN.1990.137613
关键词: Value (computer science) 、 Artificial neural network 、 Computer science 、 Computer vision 、 Artificial intelligence 、 Image (mathematics) 、 Pixel 、 Contrast (vision) 、 Image processing 、 Edge enhancement 、 Set (abstract data type)
摘要: A self-organizing artificial neural network has been described to enhance and restore gray-level images for applications in low-level image processing. The is by a set of interconnected neurons with their values equal the corresponding pixels. first-order second-order contrast links are defined among which analyzed change adaptive constrained environment. Each selected neuron only once per iteration, its value may be readjusted incrementing or decrementing current value. As result, at end each iteration data reorganized. structure algorithm proposed presented along various experimental results showing capability such