Abstract: To solve some problems on image denoising, such as losing details and falling into poor
effects, a method of image denoising is proposed based on adaptive contraction function Contourlet
transform algorithm. According to the basic Contourlet transform form and combing the soft
threshold and hard threshold contraction function, the adaptive contraction function is defined.
Experimental results show that the proposed method can greatly remove noise, effectively improve
peak signal to noise ratio, mean squared error and image enhancement factor of image quality index.
After combining the improved threshold function, the image has better visual quality.

Key words: Contourlet transform, adaptive contraction function, contract order, soft threshold, hard
threshold