|
?:abstract
|
-
Considering the disadvantages of low definition, low image contrast and brightness, inconspicuous details, which make image analysis more complicate, we developed quantum medical image processing system software It includes quantum image enhancement module, quantum image denoising module and quantum image segmentation module, which respectively study the quantum enhancement algorithm, quantum denoising algorithm and quantum segmentation algorithm Quantum denoising algorithm firstly add noise to the image and then carries out a logarithmic transformation and a double density dual-tree complex wavelet transform on the noise-added image, later a denoising of the wavelet coefficients based on Bayesian theory, and the Maxaposterior (MAP) is performed to estimate the variance of the double-tree complex wavelet Finally the denoised image is obtained from the inverse transform of the dual-tree complex wavelet Quantum enhancement algorithm improves image quality through quantum inspired and unsharp masking First, a quantum enhancement operator based on quantum superposition state theory was constructed to enhance image contrast ratio, then the processed image quality was improved by unsharp masking Quantum segmentation algorithm searches automatically the optimal threshold through improved quantum genetic algorithm, which reduces the complexity of program and improves the information entropy compared with traditional methods More image information can be retained and more ideal segmentation effect is realized through the algorithm Experiment show that the peak signal-to-noise ratio (PSNR) for the quantum algorithm is improved by over 2dB and the edge retention index (EPI) is 0 1 higher than that for common methods, image information entropy and clarity index are significantly improved © 2020 SPIE
|
![[This page as RDF]](https://research.tib.eu/covid-19/static/rdf-icon.gif){kind=icon}