DocumentCode :
2102058
Title :
Saliency-guided compressive fluorescence microscopy
Author :
Schwartz, S. ; Wong, Alexander ; Clausi, David A.
Author_Institution :
Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON, Canada
fYear :
2012
fDate :
Aug. 28 2012-Sept. 1 2012
Firstpage :
4365
Lastpage :
4368
Abstract :
A novel saliency-guided approach is proposed for improving the acquisition speed of compressive fluorescence microscopy systems. By adaptively optimizing the sampling probability density based on regions of interest instead of the traditional unguided random sampling approach, the proposed saliency-guided compressive fluorescence microscopy approach can achieve high-quality microscopy images using less than half of the number of fluorescence microscopy data measurements required by existing compressive fluorescence microscopy systems to achieve the same level of quality.
Keywords :
biological techniques; biology computing; cellular biophysics; fluorescence; image reconstruction; image sampling; optical images; optical microscopy; optimisation; probability; random processes; acquisition speed; adaptive sampling probability density based optimisation; cells; fluorescence microscopy data measurements; high-quality microscopy images; image reconstruction; regions-of-interest; saliency-guided compressive fluorescence microscopy; traditional unguided random sampling approach; Image coding; Image reconstruction; Microscopy; Noise; Noise measurement; Optical microscopy; Pollution measurement; Algorithms; Data Compression; Image Enhancement; Image Interpretation, Computer-Assisted; Microscopy, Fluorescence; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE
Conference_Location :
San Diego, CA
ISSN :
1557-170X
Print_ISBN :
978-1-4244-4119-8
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/EMBC.2012.6346933
Filename :
6346933
Link To Document :
بازگشت