A new modified neutrosophic set segmentation approach. (January 2018)

• Record Type: Journal Article
• Authors: Sert, Eser
• Is Part Of: Computers & electrical engineering. Volume 65(2018)
• Page Start: 576
• Page End: 592
• Publication Date: 2018-01
• Subjects: Neutrosophic set -- Neutrosophy -- Otsu's method -- Fuzzy C-means -- 3D segmentation -- 3D modeling -- Entropy norm -- Clustering; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.01.017
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Neutrosophic Set (NS) is based on the neutrosophy theory. NS used in this study is a modified structure and runs Norm entropy-based. The main purpose of this study is to improve the quality of 3D modeling. Abstract: Segmentation is paramount to 3D video systems employing multi-view video-plus-depth data (MVD) to implement free-viewpoint navigation and comfortable 3D viewing, modeling, and comprehension. The Neutrosophic Set (NS) concept relies on the neutrosophy theory dealing with structures, and it focuses on the origin, scope, and nature of neutralities. NS used in this study is norm-entropy-based, and it is called Modified Neutrosophic Set Segmentation (MNSS). 3D modeling method via MNSS (3DMM_MNSS) proposed in this study improves the quality of single object 3D modeling through an NS stratagem called MNSS. 3DMM_MNSS is compared with 3D modeling method via OATS (3DMM_OATS) and with the 3D modeling method via FCMS (3DMM_FCMS). MNSS improves the quality of 3D modeling and prevents the problems arising from the depth map imprecision in terms of Figure of Merit (FOM), the Peak Signal-to-Noise Ratio (PSNR), and the Uniformity Measure (UM) as performance metrics. Graphical abstract: