Detection of Cell Membranes in Human Corneal Endothelial Micrograms Using Mathematical Morphology
Authors:
- Akira HasegawaAHAkira Hasegawa
- Kazuyoshi ItohKIKazuyoshi Itoh
- Yoshiki IchiokaYIYoshiki Ichioka
- 1 March 1992
- journal article
- Published by IOP Publishing in Japanese Journal of Applied Physics
- Vol. 31 (3R)
Abstract
We propose a method for computer-assisted detection of cell membranes in human corneal endothelial micrograms. Detection of the cell boundary is generally achieved by manually tracing the cell membranes in the micrograms. However, manual tracing is subjective and time consuming. Our method uses modified morphological filters to smooth out noise while keeping linear structures in the image. The processed image is then binarized by template matching. Since the resultant membranes in the image normally consist of broken lines, they must be connected. The identical morphological operation is used again to connect the broken lines. The shapes of cells derived by this method overlap well with those defined by manual tracing.Keywords
This publication has 6 references indexed in Scilit:
- Image Analysis Using Mathematical MorphologyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1987
- Grayscale morphologyComputer Vision, Graphics, and Image Processing, 1986
- The Effects of Hard and Soft Contact Lenses on the Corneal EndotheliumAmerican Journal of Ophthalmology, 1986
- Tissue section analysis: Feature selection and image processingPattern Recognition, 1981
- Scanning mirror microscope with optical sectioning characteristics: applications in ophthalmologyApplied Optics, 1980
- Two graph searching techniques for boundary finding in white blood cell imagesComputers in Biology and Medicine, 1978