二维直方图重建和降维的Otsu阈值分割算法

A Otsu Threshold Segmentation Method Based on Rebuilding and Dimension Reduction of the Two-Dimensional Histogram

指出二维直方图直分法中存在区域划分不合理和抗噪性差问题,提出一种新的阈值分割方法,导出有关计算公式。首先分析噪声点在二维直方图中分布情况,通过重建二维直方图减弱了噪声对阈值分割的干扰;然后将二维直方图区域划分由四分法改为二分法,使得阈值搜索的空间维度从二维降到一维;最后分别给出现有二维直方图分割算法和本文方法的仿真结果。理论分析和实验结果表明,该方法可以运用于几乎所有基于二维直方图的阈值分割,特别是对受噪声污染的图片进行阈值分割时,能使分割后的图片内部均匀、边界准确、抗噪性更稳健,所需运行时间大幅减少。

The issue of poor resistance to noise and unreasonable is pointed out based ontwo-dimensional histogram regional straight points method. A new threshold segmentation method isproposed, and the calculation formula of the method is deduced. Firstly, in this method, noiseinterference weakened for threshold＇s segmentation through the reconstruction of two-dimensionalhistogram based on detailed analysis of noise distribution in the two-dimensional histogram, and then,the region division is transfered from eight partitions into two partitions in two-dimensionalhistogram. Thus the two-dimension search space of threshold is reduced to one-dimension. Finally,simulation results of existing two-dimensional histogram segmentation algorithm and our method aregiven respectively. Theoretical analysis and experimental results show that our method could be usedin nearly all the two-dimensional histogram threshold segmentation, especially in thresholdsegmentation with the contaminated image. It makes the inner part uniform, the edge accurate in thethreshold image and has better tolerance capability to noise. The running time is significantlyreduced.