dc.description.abstract |
Image has a very important role in supporting information delivery, but sometimes it is not followed by good image quality. Disturbances are found in the image, for example the image has noise, so a method is needed to reduce the noise contained in the image. Image restoration is a technique in repairing images that have been degraded or damaged such as noise. One of the techniques in image restoration is filtering. The filtering technique used in this study is to compare the performance of Mean Filter, Median Filter, and Alpha-Trimmed Mean Filter methods in reducing noise so it can be determined which method is better applied in image restoration, especially for specklenoise and rayleighnoise. The parameter used to analyze the effect of specklenoise and rayleighnoise on the comparative performance of the filtering method are MSE, PSNR and running time during noise reduction. The purpose of the study is to improve the images quality affected by noise by performing a filtering process using the Mean Filter, Median Filter and Alpha-Trimmed Mean Filter methods. The test results are the performance of the Mean Filter and Median Filter methods in reducing speckle noise and rayleigh noise produces almost the same with image quality compared to the Alpha-Trimmed Mean Filter method. However, based on the MSE, PSNR and Running Time parameters, the performance of the Alpha-Trimmed Mean Filter method is the best in reducing speckle noise and rayleigh noise.
Keyword : Noise Reduction, Speckle Noise, Rayleigh Noise, Mean Filter, Median Filter, Alpha-Trimmed Mean Fiter, MSE, PSNR
| en_US |