scholarly journals A Review on Machine and Deep Learning for Semiconductor Defect Classification in Scanning Electron Microscope Images

2021 ◽  
Vol 11 (20) ◽  
pp. 9508
Author(s):  
Francisco López de la Rosa ◽  
Roberto Sánchez-Reolid ◽  
José L. Gómez-Sirvent ◽  
Rafael Morales ◽  
Antonio Fernández-Caballero
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Defect Detection ◽  
Scoping Review ◽  
Semiconductor Manufacturing ◽  
Manufacturing Industry ◽  
Future Research ◽  
Wide Range ◽  
Scanning Electron

Continued advances in machine learning (ML) and deep learning (DL) present new opportunities for use in a wide range of applications. One prominent application of these technologies is defect detection and classification in the manufacturing industry in order to minimise costs and ensure customer satisfaction. Specifically, this scoping review focuses on inspection operations in the semiconductor manufacturing industry where different ML and DL techniques and configurations have been used for defect detection and classification. Inspection operations have traditionally been carried out by specialised personnel in charge of visually judging the images obtained with a scanning electron microscope (SEM). This scoping review focuses on inspection operations in the semiconductor manufacturing industry where different ML and DL methods have been used to detect and classify defects in SEM images. We also include the performance results of the different techniques and configurations described in the articles found. A thorough comparison of these results will help us to find the best solutions for future research related to the subject.

scholarly journals Robust Deep-learning Based Autofocus Score Prediction for Scanning Electron Microscope

2020 ◽  
Vol 26 (S2) ◽  
pp. 702-705
Author(s):  
Hyun Jong Yang ◽  
Moohyun Oh ◽  
Jonggyu Jang ◽  
Hyeonsu Lyu ◽  
Junhee Lee
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Scanning Electron

Charge Contrast Imaging (CCI) in the Environmental Scanning Electron Microscope: Optimizing Operating Parameters for Calcite

2001 ◽  
Vol 7 (S2) ◽  
pp. 780-781
Author(s):  
Eric Doehne ◽  
David Carson
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Defect Density ◽  
Imaging System ◽  
Environmental Scanning Electron Microscope ◽  
Small Scale ◽  
Environmental Scanning ◽  
Contrast Imaging ◽  
Wide Range ◽  
Scanning Electron

Charge contrast imaging (CCI) is a useful new method for imaging sub-micron features in crystalline materials using the unique gas/ion/electron imaging system of the environmental scanning electron microscope (Griffin, 1997; Doehne, 1998). Crystal growth zoning, microfractures, solution boundaries, and areas of chemical alteration or recrystallization can be imaged in a wide range of materials (Griffin, 2000; Watt, et al. 2000). While not fully understood, charge contrast images reflect differences in the ability of materials to accept, store and discharge deposited electrons from the primary electron beam. These differences are expressed, in turn, as contrasts in secondary electron emission from flat samples (e.g. these contrasts are not related to topography, as is usually the case). Charge contrast appears be related to differences in electronic properties which are often controlled by defect density. CCI is also affected by small-scale physical defects (such as microfractures) which appear to affect the distribution and timing of charge buildup and discharge in the sample (Johansen, et al. 1997).

scholarly journals Determination of the Effective Detector Area of an Energy-Dispersive X-Ray Spectrometer at the Scanning Electron Microscope Using Experimental and Theoretical X-Ray Emission Yields

2016 ◽  
Vol 22 (6) ◽  
pp. 1360-1368 ◽  
Author(s):  
Mathias Procop ◽  
Vasile-Dan Hodoroaba ◽  
Ralf Terborg ◽  
Dirk Berger
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Count Rate ◽  
Effective Area ◽  
Energy Dispersive ◽  
X Ray ◽  
Active Sensor ◽  
Wide Range ◽  
Specific Geometry ◽  
Scanning Electron

AbstractA method is proposed to determine the effective detector area for energy-dispersive X-ray spectrometers (EDS). Nowadays, detectors are available for a wide range of nominal areas ranging from 10 up to 150 mm2. However, it remains in most cases unknown whether this nominal area coincides with the “net active sensor area” that should be given according to the related standard ISO 15632, or with any other area of the detector device. Moreover, the specific geometry of EDS installation may further reduce a given detector area. The proposed method can be applied to most scanning electron microscope/EDS configurations. The basic idea consists in a comparison of the measured count rate with the count rate resulting from known X-ray yields of copper, titanium, or silicon. The method was successfully tested on three detectors with known effective area and applied further to seven spectrometers from different manufacturers. In most cases the method gave an effective area smaller than the area given in the detector description.

scholarly journals The Role of Aragonite in Producing the Microstructural Diversity of Serpulid Skeletons

Minerals ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1435
Author(s):  
Olev Vinn
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Powder Diffraction ◽  
Deep Ocean ◽  
X Ray ◽  
Prismatic Structure ◽  
Wide Range ◽  
Different Types ◽  
Scanning Electron

Aragonite plays an important role in the biomineralization of serpulid polychaetes. Aragonitic structures are present in a wide range of serpulid species, but they mostly belong to one clade. Aragonitic structures are present in a wide range of marine environments, including the deep ocean. Aragonitic tube microstructures were studied using a scanning electron microscope. X-ray powder diffraction was used to identify the aragonite. Aragonite is used to build five different types of microstructures in serpulid tubes. The most common aragonitic irregularly oriented prismatic structure (AIOP) is also, evolutionarily, the most primitive. Some aragonitic microstructures, such as the spherulitic prismatic (SPHP) structure, have likely evolved from the AIOP structure. Aragonitic microstructures in serpulids are far less numerous than calcitic microstructures, and they lack the complexity of advanced calcitic microstructures. The reason why aragonitic microstructures have remained less evolvable than calcitic microstructures is currently unknown, considering their fit with the current aragonite sea conditions (Paleogene–recent).

Analyze of scanning electron microscope images using deep learning for calcium carbonate polymorph detection

2020 ◽  
Vol 20 (2020) ◽  
pp. 416-417
Author(s):  
Caio Marcellos ◽  
Amaro Gomes Barreto Jr ◽  
Juliana Braga Rodrigues Loureiro ◽  
Elvis do Amaral Soares ◽  
Danilo Naiff ◽  
...  
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Calcium Carbonate ◽  
Scanning Electron Microscope ◽  
Microscope Images ◽  
Scanning Electron

Study of In Vivo Plaque Formation

1976 ◽  
Vol 55 (3) ◽  
pp. 481-488 ◽  
Author(s):  
James N. Connor ◽  
Charles M. Schoenfeld ◽  
Ross L. Taylor
Keyword(s):  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Plaque Formation ◽  
Sem Micrographs ◽  
Wide Range ◽  
Artificial Surfaces ◽  
Range Of Variation ◽  
Scanning Electron

A technique was developed by which plaque accumulations on intraoral artificial surfaces could be viewed with a scanning electron microscope (SEM). Micrographs of two plaque specimens from a given individual appeared similar; however, plaque specimens from different individuals encompassed a wide range of variation in terms of content and thickness.

scholarly journals A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method

Scanning ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Lun Zhao ◽  
Yunlong Pan ◽  
Sen Wang ◽  
Liang Zhang ◽  
Md Shafiqul Islam
Keyword(s):  
Deep Learning ◽  
Electron Microscope ◽  
Scanning Electron Microscope ◽  
Crack Detection ◽  
Rapid Development ◽  
Detection Accuracy ◽  
Learning Method ◽  
Sem Images ◽  
Bounding Boxes ◽  
Scanning Electron

The scanning electron microscope (SEM) is widely used in the analysis and research of materials, including fracture analysis, microstructure morphology, and nanomaterial analysis. With the rapid development of materials science and computer vision technology, the level of detection technology is constantly improving. In this paper, the deep learning method is used to intelligently identify microcracks in the microscopic morphology of SEM image. A deep learning model based on image level is selected to reduce the interference of other complex microscopic topography, and a detection method with dense continuous bounding boxes suitable for SEM images is proposed. The dense and continuous bounding boxes were used to obtain the local features of the cracks and rotating the bounding boxes to reduce the feature differences between the bounding boxes. Finally, the bounding boxes with filled regression were used to highlight the microcrack detection effect. The results show that the detection accuracy of our approach reached 71.12%, and the highest mIOU reached 64.13%. Also, microcracks in different magnifications and in different backgrounds were detected successfully.

Sign in / Sign up

Export Citation Format

Share Document