Skip to main navigation Skip to search Skip to main content

Development of laser speckle metrology and its identification techniques

  • Ruey Nan Yeh*
  • , Po Yi Sung
  • , Chia Hung Yeh
  • , Wen Yu Tseng
  • , Jin Wei Yeh
  • , Yen Hao Chang
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The main goal of this paper is to identify last speckle images rapidly. Digital image processing techniques are employed to analyze the characteristics of laser speckle images and match them up to achieve laser speckle image identification. Besides the database is built to accelerate the identification process and further enhance its practicability. In terms of building the database, Gabor filter is utilized to enhance the extracted characteristics as well as to generate the feature vectors. The final step is adopting K-means clustering to build the classification model of feature vectors. The process of identifying laser speckle images is described as follows. Through experiments we observed that scale invariant feature transform (SIFT) can extract features of laser speckle images very well. However the drawback is that it took too much time to compute and match up those features, which is not suitable for fast laser speckle identification. Therefore the proposed method took enhance SIFT as backbone. Experimental results demonstrate that the retrieval performance of the proposed method is accurate when the database size contains 516 images.

Original languageEnglish
Title of host publicationProceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011
PublisherIEEE Computer Society
Pages1381-1385
Number of pages5
ISBN (Print)9781457703065
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event10th International Conference on Machine Learning and Cybernetics, ICMLC 2011 - Guilin, Guangxi, China
Duration: 2011 Jul 10 → 2011 Jul 13

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume3
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference10th International Conference on Machine Learning and Cybernetics, ICMLC 2011
Country/TerritoryChina
CityGuilin, Guangxi
Period2011/07/10 → 2011/07/13

Keywords

  • Gabor feature
  • K-means
  • Laser speckle image
  • SIFT

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computational Theory and Mathematics
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Development of laser speckle metrology and its identification techniques'. Together they form a unique fingerprint.

Cite this