提出了用于激光共焦显微生物医学图象分割的循环递增阈值分割法。
A recursively increasing threshold method for the segmentation of laser scanning confocal microscopic (LSCM) biomedical images is presented.
首先用阈值分割法去除红毛丹背景，然后用模糊C均值聚类方法来分割果肉区域。
The rambutan flesh was segmented using the FCM (fuzzy C-mean) clustering method after removing the background of the image.
提出了一种基于最大相关准则的图像阈值分割法。该算法比基于最大熵原理的图像分割法更简便。
Based on maximum relativity criterion, a new thresholding algorithm for image segmentation is proposed which is more simple than the thresholding algorithm based on maximum entropy.
以全局阈值为基础，用邻域平均灰度与全局阈值之差的加权值对其进行调整，从而形成一种新的动态阈值分割法。
Based on global threshold, a new dynamic thresholding approach is proposed which is adjusted with th weighting of the difference between neighbor average grey and global threshold.
本文在介绍了三种具有代表性的图像阈值分割法的基础上，通过对它们的性能进行分析比较，给出了这三种阈值分割法的适用范围。
Based on the representation of three typical thresholding methods for image segmentation and the analysis of their performances, the scope of each method was mentioned.
采用基于最大类间方差的遗传分割法通过反复迭代搜索得到较优的分割阈值，实现了憎水性图像的准确分割，可满足后续基于BP神经网络的憎水性等级的判定。
The optimum threshold value was obtained and accurate segmentation of hydrophobic image was realized, which can meet the need of the classification of hydrophobicity levels based on BP neural network.
采用基于最大类间方差的遗传分割法通过反复迭代搜索得到较优的分割阈值，实现了憎水性图像的准确分割，可满足后续基于BP神经网络的憎水性等级的判定。
The optimum threshold value was obtained and accurate segmentation of hydrophobic image was realized, which can meet the need of the classification of hydrophobicity levels based on BP neural network.
应用推荐