The paper presents two-dimensional non-linear weighted average filter, for which weights were selected using fuzzy logic. The proposed algorithm was tested using test images in 256 shades of grey, jammed using white noise characterised by normal distribution. The mean square error (MSE) measure was used as a criterion for filtration quality assessment. The PIF coefficient was employed to assess filter impact on image structure.
The authors presented in the study human voice recognition algorithm, which functioning is based on analysis of spectrograms with MSE (mean square error) quality measure utilization, which is employed for digital images comparing. The algorithm of human voice recognition proposed in the article was practically used for voice control of visual supervision system.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.