A Novel Image Segmentation Algorithm Based on Neutrosophic Filtering and Level Set

Abstract

Image segmentation is an important step in image processing and analysis, pattern recognition, and machine vision. A few of algorithms based on level set have been proposed for image segmentation in the last twenty years. However, these methods are time consuming, and sometime fail to extract the correct regions especially for noisy images. Recently, neutrosophic set (NS) theory has been applied to image processing for noisy images with indeterminant information. In this paper, a novel image segmentation approach is proposed based on the filter in NS and level set theory. At first, the image is transformed into NS domain, which is described by three membership sets (T, I and F). Then, a filter is newly defined and employed to reduce the indeterminacy of the image. Finally, a level set algorithm is used in the image after filtering operation for image segmentation. Experiments have been conducted using different images. The results demonstrate that the proposed method can segment the images effectively and accurately. It is especially able to remove the noise effect and extract the correct regions on both the noise-free images and the images with different levels of noise.