Resumen
An algorithm called ICM-TM to reduce the effect of Gaussian noise in grayscale images is proposed. It is based on the operation of the wellknown Intersection Cortical Model (ICM), a kind of Pulse-Coupled Artificial Neural Network. A Time Matrix (TM) provides information about the iteration when the neuron fires for first time. Each neuron corresponds to a pixel. A selective filtering criteria that combines the median and average operators using the neurońs activation time is established. The performance of the proposed algorithm is evaluated experimentally with varying degrees of Gaussian noise. Simulation results show that the effectiveness of the method is superior to the median filter, Gaussian filter, Sigma filter, Wiener filter and to the Pulse-Coupled Neural Networks with the Null Interconnections (PCNNNI). Results are mainly provided by the parameter Peak Signal to Noise Ratio (PSNR).
Título traducido de la contribución | Using pulse coupled neural networks to improve image filtering contaminated with Gaussian noise |
---|---|
Idioma original | Español |
Páginas (desde-hasta) | 381-395 |
Número de páginas | 15 |
Publicación | Computacion y Sistemas |
Volumen | 21 |
N.º | 2 |
DOI | |
Estado | Publicada - 2017 |
Palabras clave
- Gaussian noise
- Intersection cortical model (ICM)
- Peak signal to noise ratio (PSNR)
- Wiener filter