Image Segmentation Based on 2D Otsu Method with Histogram Analysis
Image Segmentation Based on 2D Otsu Method with Histogram Analysis
复制标题
DOI：
10.1109/csse.2008.206
复制
发表时间：
2008-12
期刊：
影响因子：
--
通讯作者：
Jun Zhang;Jinglu Hu
中科院分区：
文献类型：
--
作者：
Jun Zhang;Jinglu Hu
图像分割在图像分析和计算机视觉系统中发挥着重要作用。在各种图像分割方法中，自动阈值分割方法因其实现简单、节省时间等优点而得到广泛应用。大津法是一种常用的阈值分割方法。二维（2D）大津方法比一维（1D）方法在低信噪比的图像分割中表现得更好。但只有当每类像素的数目接近时，它才能给出令人满意的结果。否则，会产生不正确的结果。本文采用二维直方图投影对大津阈值进行校正。通过二维直方图在x、y轴上的投影得到一维直方图，并提出了一种基于小波变换的投影直方图极值快速搜索算法。实验结果表明，该方法优于传统的大津方法对我们的肾活检样本。
Image segmentation plays an important role in image analysis and computer vision system. Among all segmentation techniques, the automatic thresholding methods are widely used because of their advantages of simple implement and time saving. Otsu method is one of thresholding methods and frequently used in various fields. Two-dimensional (2D) Otsu method behaves well in segmenting images of low signal-to-noise ratio than one-dimensional (1D). But it gives satisfactory results only when the numbers of pixels in each class are close to each other. Otherwise, it gives the improper results. In this paper, 2D histogram projection is used to correct the Otsu threshold. The 1D histograms are acquired by 2D histogram projection in x and y axes and a fast algorithm for searching the extrema of the projected histogram is proposed based on the wavelet transform in this paper. Experimental results show that the proposed method performs better than the traditional Otsu method for our renal biopsy samples.