Abstract
The noninvasive imaging techniques of phase contrast and differential interference contrast microscopy have been widely used to capture time-lapse images to monitor the behavior of transparent cells without staining or altering them. Due to the unique optical principle, the microscopy images contain special artifacts such as the halo and shade-off, which hinder image segmentation-a cornerstone of many microscopy image analysis tasks. In this chapter, first we study the optical principles of these microscopy techniques and derive a mathematical model to approximate their image formation processes. Then we develop a few image restoration methods based on the imaging model that reduce artifacts, enhance the image contrast, and enrich the image features. Finally, we demonstrate that the image segmentation can benefit greatly from optics-based image restoration.
| Original language | English |
|---|---|
| Title of host publication | Computer Vision for Microscopy Image Analysis |
| Publisher | Elsevier |
| Pages | 13-41 |
| Number of pages | 29 |
| ISBN (Electronic) | 9780128149720 |
| DOIs | |
| State | Published - Jan 1 2020 |
Keywords
- DIC microscope
- Image formation model
- Image restoration
- Image segmentation
- Phase contrast microscope
Fingerprint
Dive into the research topics of 'Microscopy image formation, restoration, and segmentation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver