Research And Application Of Image Segmentation Algorithm Based On The Theory Of Hesitant Neutrosophic

Image segmentation is the foundation and key task of image processing.Due to the uncertainty information of the image itself,when the uncertain information in the image cannot be used,the image segmentation result will be inaccurate.As a generalization of fuzzy set and intuitionistic fuzzy set,the neutrosophic set can be used to describe incomplete and inaccurate information of image.neutrosophic set can quantify the fuzzy and uncertain information of things,so it is used in the field of image processing.The hesitant neutrosophic set is formed on the basis of hesitancy set and neutrosophic set,It considers the hesitation degree of information in neutrosophic set.Based on the image processing of neutrosophic set,an image segmentation method of hesitant neutrosophic set is proposed in this paper,and the effectiveness of this method is proved by experiments.In this paper,the image segmentation of images with Gaussian noise and saltand-pepper noise and single plaque dermoscope images with noise background,gray uneven and fuzzy is studied.The main research contents and innovations are as follows:(1)this paper proposes a hesitant neutrosophic set image segmentation method,according to the related definitions and properties of hesitant neutrosophic set,define different hesitant neutrosophic image,design hesitation degree function to express the image of the target information to the subsequent extraction,then defines the image entropy to judge different hesitant neutrosophic image,Finally,the clustering method is used to segment the image.(2)Aiming at the shortcomings of the traditional regularized level set segmentation method,an image segmentation method based on hesitant neutrosophic set and level set is proposed.Firstly,the original image is transformed into the hesitant neutrosophic image,the traditional regularization level set is improved,the original edge stop function is improved,and a new gray difference energy term is constructed.The gray difference energy term considers the gray information inside and outside the level set,which overcomes the defect that the traditional level set only considers the gradient information.The improved regularized level set is used to segment the image of hesitant neutrosophic set,the validity of this method for single plaque dermoscopic image segmentation is verified by several indexes.