Estimation of Average Cell Shape from Digital Images of Cellular Surfaces

  • Authors:
  • Affiliations:
  • Venue:
  • CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

A method is proposed to determine the average cellulargeometry in high-resolution images of embryonic epithelia.The concept of a ýcomposite cellý is used to represent the averagecell shape. This composite cell can provide evidence of stressespresent in the epithelia. A new adaptive contrast enhancementroutine is applied to the input image first, followed by aniterative watershed segmentation. The composite cell is calculatedfrom the segmentation results. Qualitative results show that thiscomputationally inexpensive algorithm produces accurate resultsfor a variety of image sizes, contrast levels, cell shapes andappearances.