Comparison of the Methods of Image Slicing After Initial Image Processing Using the Statistical Confidence Limits Technique

Abstract

The use of image segmentation in image processing is of great importance in analyzing and extracting information from images, and one of the most important segmentation techniques is the threshold technique, which is considered one of the simplest techniques of image division in image processing. The statistical methods play an important role in the process of image segmentation. Statistical confidence in image processing, preliminary processing, as it removed noise from the images, and here the obscure noise was used. After that, the resulting images were cut, the initial processing process with the global Otsu threshold technology and a group of local techniques, namely Niblack, sauvola and local Bernsen, and the split image quality was measured by statistic measures namely Jaccard Similarity Coefficient and Maximum Signal to Noise Ratio (PSNR). as was the application of the methods mentioned on the images and the comparison between the methods of treatment in order to obtain the best results that appear in the image in which it appears and reduce noise.