PROJECT TITLE :
Performance Improvement of Average Based Spatial Filters through Multilevel Preprocessing using Wavelets
Image denoising filters supposed to get rid of Gaussian noise, principally exploit a procedure referred to as spatial averaging. Quite a ton of averaging approaches are developed and varied fall in the class of either pixel-based or patch-primarily based or diffusion-based mostly approach. Whereas the designed filters lose the noise, the high frequency data will conjointly be degraded, because the filters work into a nature of integration. To preserve the high frequency information and hence the denoising performance, we propose a preprocessing filter designed in the wavelet domain, will be placed prior to the given existing spatial domain averaging filter. The proposed filter enhances high frequency information of given noisy image and clearly this enhanced data will conjointly be degraded at some extent by the next spatial domain filters. Accordingly, proposed preprocessing filter and existing average based mostly spatial domain filter on an entire offers improved denoising performance. Simulation experiments have been conducted and it's proved that the proposed preprocessing filter actually improves the denoising results of existing commonplace spatial domain filtering such as Anisotropic filtering, Bilateral filtering, Non native means that filtering and recently proposed Probabilistic non local suggests that filtering in terms of peak signal to noise ratio (PSNR) and structural similarity index (SSIM).
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here