Open AccessWavelet method of edge detection in images with high-noise level
Author(s) -
T. Niedziela
Publication year - 2020
Publication title -
transengin
Language(s) - English
Resource type - Journals
eISSN - 2658-2120
pISSN - 2658-1698
DOI - 10.24136/tren.2020.009
Subject(s) - haar wavelet , wavelet transform , wavelet , haar , gauss , artificial intelligence , transformation (genetics) , wavelet packet decomposition , edge detection , second generation wavelet transform , stationary wavelet transform , pattern recognition (psychology) , computer science , mathematics , computer vision , continuous wavelet transform , discrete wavelet transform , bandwidth (computing) , harmonic wavelet transform , gaussian noise , image (mathematics) , image processing , telecommunications , physics , biochemistry , chemistry , quantum mechanics , gene
In the paper a mathematical model addressed to non-sharp edges in the images is proposed. This model is based on and integral transform with Haar-Gauss wavelet and matching algorithm of bandwidth, such model is used to detection of the edges in images with high-level noises, both in the x plane and the frequency domains. There is shown that applying the integral Haar-Gaussian transformation the detection of single and double edges is possible. Demonstrated in the paper results confirm that wavelet transform supported by the matching wavelet algorithm of wavelength bandwidth make an important exploration tool of the images with the edges possessing a large depth of sharpness.