Research On X-ray Image De-noising And Target Extraction Based On ICA

X-ray medical image can examine diseased tissue of patients and has important reference value for medical diagnosis. Traditional X-ray images have noise, poor level sense and blocked aliasing organs, this paper proposes a method of independent component analysis algorithm(ICA) to denoise image and separate the target objects.In this paper ICA was applied to image de-noising of theory analysis and simulation experiments, using two ICA de-noising methods to the sequences of X-ray images,evaluating the output images with subjective and objective standards.Based on ICA combined with sparse coding shrinkage method for image de-noising, target images are divided into smaller image sequence by setting sliding window. Signals distributed sparsely are removed noise to retain useful information by setting soft threshold function.Based on FastICA algorithm for image sequence,the number of input images for image denoising effect is obvious as well as the influence on computational complexity and time complexity of the algorithm.The experimental results show that ICA image denoising methods are better to retain the image information, denoising effect meets subjective evaluation criteria.On the theoretical analysis and simulation of X-ray medical image target extraction in ICA,firstly image de-noising preprocessing ensures the accuracy of target extraction based on independent component analysis and sparse code shrinkage. Then according to the main proportion of organ in the images, aliasing thickness matrix of each pixel was isolated. Finally independent component analysis obtains convergence matrix to reconstruct the target object with blind separation theory. In the ICA algorithm, it found that when the number is more than 40, the target objects separate successfully with the aid of subjective evaluation standard. And when the amplitudes of the scale are in the [25,45] interval, the target images have high contrast and less distortion. The three-dimensional figure of Peak signal to noise ratio(PSNR) shows that the.different convergence times and amplitudes have a greater influence on image quality. The contrast and edge information of experimental images achieve better effects with the convergence times 85 and amplitudes 35 in the ICA algorithm.