Performance study of several global thresholding techniques for segmentation
Computer Vision, Graphics, and Image Processing
Extraction of binary character/graphics images from grayscale document images
CVGIP: Graphical Models and Image Processing
A new approach for multilevel threshold selection
CVGIP: Graphical Models and Image Processing
Improvement of “integrated function algorithm” for binarization of document images
Pattern Recognition Letters
Fuzzy Algorithms: With Applications to Image Processing and Pattern Recognition
Fuzzy Algorithms: With Applications to Image Processing and Pattern Recognition
Hi-index | 0.00 |
We present new algorithms for segmenting neuron images which are taken from cells being grown in culture with oxidative agents. Information from changing images can be used to compare changes in neurons from the Zellweger mice to those from normal mice. Image segmentation is the first and major step for the study of these different types of processes in neuron cells. It is difficult to do it as these neuron cell images from stained fields and unimodal histograms. In this paper we develop an innovative strategy for the segmentation of neuronal cell images which are subjected to stains and whose histograms are unimodal. The proposed method is based on logical analysis of grey difference. Two key parameters, window width and logical threshold, are automatically extracted to be used in logical thresholding method. Spurious regions are detected and removed by using hierarchical filtering window. Experiment and comparison results show the efficient of our algorithms.