3DSEM++: Adaptive and intelligent 3D SEM surface reconstruction. (August 2016)

• Record Type: Journal Article
• Authors: Tafti, Ahmad P.; Holz, Jessica D.; Baghaie, Ahmadreza; Owen, Heather A.; He, Max M.; Yu, Zeyun
• Is Part Of: Micron. Volume 87(2016:Aug.)
• Page Start: 33
• Page End: 45
• Publication Date: 2016-08
• Subjects: 3D microscopy vision -- Scanning electron microscope (SEM) -- 3D SEM surface reconstruction; Microscopy -- Periodicals; Electron Probe Microanalysis -- Periodicals; Microscopy -- Periodicals; Microscopie -- Périodiques; Microscopy; Periodicals; 502.82
• DOI: 10.1016/j.micron.2016.05.004
• Languages: English
• ISSNs: 0968-4328

Abstract

Abstract : Highlights: Using advanced computational technologies, such as multi-view geometry and machine learning strategies, an attempt was made to design and develop a 3D SEM surface reconstruction method in an adaptive and intelligent fashion. We analyzed the qualitative and quantitative attributes of our proposed framework by using both real and synthetic data. The results have been promising. This contribution is expected to highlight the important roles, applications, and advantages of the supervised machine learning algorithms and statistical analysis in the area of 3D microscopy vision. Abstract: Structural analysis of microscopic objects is a longstanding topic in several scientific disciplines, such as biological, mechanical, and materials sciences. The scanning electron microscope (SEM), as a promising imaging equipment has been around for decades to determine the surface properties (e.g., compositions or geometries) of specimens by achieving increased magnification, contrast, and resolution greater than one nanometer. Whereas SEM micrographs still remain two-dimensional (2D), many research and educational questions truly require knowledge and facts about their three-dimensional (3D) structures. 3D surface reconstruction from SEM images leads to remarkable understanding of microscopic surfaces, allowing informative and qualitative visualization of the samples being investigated. In this contribution, we integrate several computational technologies including machine learning, contrario methodology, and epipolar geometry to design and develop a novel and efficient method called 3DSEM++ for multi-view 3D SEM surface reconstruction in an adaptive and intelligent fashion. The experiments which have been performed on real and synthetic data assert the approach is able to reach a significant precision to both SEM extrinsic calibration and its 3D surface modeling.