彩色图像的矢量阈值自适应分割算法

Adaptive Vector Threshold Segmentation Algorithm for Color Image

针对彩色图像,提出了一种矢量阈值的自适应分割算法,该算法中的阈值是一个矢量．在图像分割时,通过先求取图像像素矢量与阚值矢量之间的差矢量,再根据差矢量与阈值矢量之间的夹角确定像素所属的区域(背景区域或目标区域)．同时基于类间方差法(Ostu法)给出了最佳阈值矢量选择原则——扩展类间矢量方差法,从而实现彩色图像矢量阈值的自适应分割．实验结果表明,采用此图像分割算法分割效果要优于采用灰度图像的阈值分割算法．

For color image, an adaptive vector threshold segmentation algorithm in which the threshold is a vector is presented in this PaPer. Image segmentation is divided into two steps： difference vector of pixel vector of image and threshold vector is computed at first and a pixel is confirmed which region （object region or background region） it belongs to finally. At the same time, the method for selecting optimal threshold vector called extended class vector square error is given based on class square error （Ostu method）. Therefore, adaptive vector threshold segmentation algorithm for color image is realized. Experiments results show that the image segmentation algorithm presented in this paper is better than the threshold segmentation for gray image.