| As a generalization of the fuzzy set theory and the intuitionistic fuzzy set theory,the neutrosophic set have been developed to represent uncertain,imprecise,incomplete and inconsistent information existing in the real world.The interval neutrosophic set and the multi-valued neutrosophic set are subclasses of the neutrosophic set,which describe things in the form of interval value and multi-valued,rather than just a specific number,and can retain more effective information of things.For the fuzzy information in the field of image segmentation,this dissertation proposes an image segmentation approach based on the interval neutrosophic set and multi-valued neutrosophic set.And the effectiveness of the approach is verified.The main contributions of the dissertation are as follows:(1)This dissertation introduces the interval neutrosophic image and the multi-valued neutrosophic image according to the interval neutrosophic set and the multi-valued neutrosophic set.A new image representation is defined.It can deal with the uncertainty in the image and preserve more effective information in the image.(2)This dissertation proposes an image segmentation approach based on the interval neutrosophic set and the multi-valued neutrosophic set.The image is transformed into the interval neutrosophic image and multi-valued neutrosophic image,and the contrast of the image is increased by image enhancement operations.The score function of each pixel in the interval neutrosophic image and multi-valued neutrosophic image is calculated.Then the results are combined with the clustering method to image segmentation.(3)The image segmentation method proposed in this dissertation is analyzed and the optimal pixel region value in image segmentation is calculated.The segmentation results are evaluated both subjectively and objectively.The experimental results on a variety of images demonstrate that the proposed approach can segment different sorts of images.It can not only retain the effective information of the image,but also have the noise-tolerant ability. |
