Adaptive Thresholding Based Cell Segmentation for Cell-Destruction Activity Verification

Abstract

An adaptive thresholding method used to distinguish cell boundaries in a given image is presented in this paper. A preprocessing step involves low pass filtering of the image to remove high frequency noise seen in the image. This image is now adaptively thresholded to create a binary image. The bright regions are further analyzed based on their geometrical descriptors such as area and form factor to classify them as cell or non-cell regions. Two sets of images, pulsed and non-pulsed, are available, which can be compared to determine the efficiency of the pulsing. Results for automatic segmentation are compared with those of manually obtained values to determine its efficiency.