The invention discloses an industrial
image denoising method and
system based on cardinal
number type polishing spline wavelets, and relates to the technical field of
image processing. The method comprises the steps that a cubic cardinal
number type polishing spline function serves as a scaling function, a cardinal
number type polishing spline wavelet function with an explicit analytical expression is constructed, a dual-scale equation is established, and coefficients are derived. And carrying out
frequency domain processing on the coefficient, and obtaining a reconstructed
filter impulse response coefficient according to a complete reconstruction condition, namely, a dual
wavelet dual-scale coefficient. A target industrial image is used as initial data, layer
wavelet decomposition and nonlinear adaptive threshold
processing are carried out through a
reconstruction filter and a Mallat dual-
channel filter bank to obtain approximation and detail information, then the image is reconstructed through Mallat inverse transformation, and denoising and detail protection are achieved.