Pattern recognition for MEMS images of surface topography using wavelets

Hu Kai, Jiang Xiangqian, Liu Xiaojun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Micro-Electro-Mechanical Systems (MEMS) have been growing in interest in recent years. Due to the small size of the MEMS, the traditional method of metrology measurement seriously affects the parameter of the object being measured, and high accuracy metrology cannot be acquired. MEMS microstructure images of surface are most composed of a number of steps, grooves and slots. Pattern analysis and recognition of these microstructures with linear feature is one of the key problems in metrology and testing technology of Micro-Electro-Mechanical-System (MEMS). Effective detections of these components play an important role in simplifying feature model in pattern recognition and pattern match. Traditional Linear feature detectors based on pixel processing each by each may fail to detect out lines in image with low SNR. A fast discrete beamlet transform and a novel method of linear feature detection are proposed, which can detect lines with any orientation, location and length. Experiment results prove the efficiency of the method proposed even in image with very low SNR.

Original languageEnglish
Title of host publicationMIPPR 2007
Subtitle of host publicationRemote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
EditorsYongji Wang, Bangjun Lei, Jing-Yu Yang, Jun Li, Chao Wang, Liang-Pei Zhang
PublisherSPIE
Number of pages5
Volume6790
ISBN (Print)9780819469540
DOIs
Publication statusPublished - 14 Nov 2007
EventInternational Symposium on Multispectral Image Processing and Pattern Rrecognition - Wuhan, China
Duration: 15 Nov 200717 Nov 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
PublisherSPIE
Volume6790
ISSN (Print)0277-786X

Conference

ConferenceInternational Symposium on Multispectral Image Processing and Pattern Rrecognition
CountryChina
CityWuhan
Period15/11/0717/11/07

Fingerprint

Surface Topography
Surface topography
Micro-electro-mechanical Systems
pattern recognition
metrology
Pattern Recognition
Pattern recognition
topography
Wavelets
Metrology
Microstructure
microstructure
slots
Feature Detection
grooves
Pattern Analysis
Feature Model
Line
pixels
High Accuracy

Cite this

Kai, H., Xiangqian, J., & Xiaojun, L. (2007). Pattern recognition for MEMS images of surface topography using wavelets. In Y. Wang, B. Lei, J-Y. Yang, J. Li, C. Wang, & L-P. Zhang (Eds.), MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications (Vol. 6790). [67905B] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6790). SPIE. https://doi.org/10.1117/12.751026
Kai, Hu ; Xiangqian, Jiang ; Xiaojun, Liu. / Pattern recognition for MEMS images of surface topography using wavelets. MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications. editor / Yongji Wang ; Bangjun Lei ; Jing-Yu Yang ; Jun Li ; Chao Wang ; Liang-Pei Zhang. Vol. 6790 SPIE, 2007. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{fee37b77e03f4286955842aac78c2365,
title = "Pattern recognition for MEMS images of surface topography using wavelets",
abstract = "Micro-Electro-Mechanical Systems (MEMS) have been growing in interest in recent years. Due to the small size of the MEMS, the traditional method of metrology measurement seriously affects the parameter of the object being measured, and high accuracy metrology cannot be acquired. MEMS microstructure images of surface are most composed of a number of steps, grooves and slots. Pattern analysis and recognition of these microstructures with linear feature is one of the key problems in metrology and testing technology of Micro-Electro-Mechanical-System (MEMS). Effective detections of these components play an important role in simplifying feature model in pattern recognition and pattern match. Traditional Linear feature detectors based on pixel processing each by each may fail to detect out lines in image with low SNR. A fast discrete beamlet transform and a novel method of linear feature detection are proposed, which can detect lines with any orientation, location and length. Experiment results prove the efficiency of the method proposed even in image with very low SNR.",
keywords = "Beamlet, Linear feature, MEMS, Image segmentation, Microelectromechanical systems, Signal to noise ratio, Hough transforms, Metrology, Pattern recognition, Image processing, Sensors, Wavelets, Feature extraction",
author = "Hu Kai and Jiang Xiangqian and Liu Xiaojun",
year = "2007",
month = "11",
day = "14",
doi = "10.1117/12.751026",
language = "English",
isbn = "9780819469540",
volume = "6790",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Yongji Wang and Bangjun Lei and Jing-Yu Yang and Jun Li and Chao Wang and Liang-Pei Zhang",
booktitle = "MIPPR 2007",
address = "United States",

}

Kai, H, Xiangqian, J & Xiaojun, L 2007, Pattern recognition for MEMS images of surface topography using wavelets. in Y Wang, B Lei, J-Y Yang, J Li, C Wang & L-P Zhang (eds), MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications. vol. 6790, 67905B, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6790, SPIE, International Symposium on Multispectral Image Processing and Pattern Rrecognition, Wuhan, China, 15/11/07. https://doi.org/10.1117/12.751026

Pattern recognition for MEMS images of surface topography using wavelets. / Kai, Hu; Xiangqian, Jiang; Xiaojun, Liu.

MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications. ed. / Yongji Wang; Bangjun Lei; Jing-Yu Yang; Jun Li; Chao Wang; Liang-Pei Zhang. Vol. 6790 SPIE, 2007. 67905B (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6790).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Pattern recognition for MEMS images of surface topography using wavelets

AU - Kai, Hu

AU - Xiangqian, Jiang

AU - Xiaojun, Liu

PY - 2007/11/14

Y1 - 2007/11/14

N2 - Micro-Electro-Mechanical Systems (MEMS) have been growing in interest in recent years. Due to the small size of the MEMS, the traditional method of metrology measurement seriously affects the parameter of the object being measured, and high accuracy metrology cannot be acquired. MEMS microstructure images of surface are most composed of a number of steps, grooves and slots. Pattern analysis and recognition of these microstructures with linear feature is one of the key problems in metrology and testing technology of Micro-Electro-Mechanical-System (MEMS). Effective detections of these components play an important role in simplifying feature model in pattern recognition and pattern match. Traditional Linear feature detectors based on pixel processing each by each may fail to detect out lines in image with low SNR. A fast discrete beamlet transform and a novel method of linear feature detection are proposed, which can detect lines with any orientation, location and length. Experiment results prove the efficiency of the method proposed even in image with very low SNR.

AB - Micro-Electro-Mechanical Systems (MEMS) have been growing in interest in recent years. Due to the small size of the MEMS, the traditional method of metrology measurement seriously affects the parameter of the object being measured, and high accuracy metrology cannot be acquired. MEMS microstructure images of surface are most composed of a number of steps, grooves and slots. Pattern analysis and recognition of these microstructures with linear feature is one of the key problems in metrology and testing technology of Micro-Electro-Mechanical-System (MEMS). Effective detections of these components play an important role in simplifying feature model in pattern recognition and pattern match. Traditional Linear feature detectors based on pixel processing each by each may fail to detect out lines in image with low SNR. A fast discrete beamlet transform and a novel method of linear feature detection are proposed, which can detect lines with any orientation, location and length. Experiment results prove the efficiency of the method proposed even in image with very low SNR.

KW - Beamlet

KW - Linear feature

KW - MEMS

KW - Image segmentation

KW - Microelectromechanical systems

KW - Signal to noise ratio

KW - Hough transforms

KW - Metrology

KW - Pattern recognition

KW - Image processing

KW - Sensors

KW - Wavelets

KW - Feature extraction

UR - http://www.scopus.com/inward/record.url?scp=42949171411&partnerID=8YFLogxK

U2 - 10.1117/12.751026

DO - 10.1117/12.751026

M3 - Conference contribution

AN - SCOPUS:42949171411

SN - 9780819469540

VL - 6790

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - MIPPR 2007

A2 - Wang, Yongji

A2 - Lei, Bangjun

A2 - Yang, Jing-Yu

A2 - Li, Jun

A2 - Wang, Chao

A2 - Zhang, Liang-Pei

PB - SPIE

ER -

Kai H, Xiangqian J, Xiaojun L. Pattern recognition for MEMS images of surface topography using wavelets. In Wang Y, Lei B, Yang J-Y, Li J, Wang C, Zhang L-P, editors, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications. Vol. 6790. SPIE. 2007. 67905B. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.751026