基于改进的k-均值聚类和数学形态学的彩色眼科图像病灶分割

THE FOCUS SEGMENTATION OF COLOR OPHTHALMOLOGIC IMAGE BASED ON MODIFIED K-MEANS CLUSTERING AND MATHEMATICAL MORPHOLOGY

病灶面积的定量化研究在眼科临床上具有重要的意义 ,为此首先需要把病灶从眼科图像中分割出来。已有的分割算法未充分利用眼科图像的整体信息 ,不适用于角膜病灶的分割。因此 ,本文提出了一种新算法 :首先利用改进的k 均值算法 ,对色度和亮度进行聚类 ,再通过数学形态学运算分割角膜病灶。实验结果表明 。

Quantitation of focus area is of great significance in the ophthalmologic diagnosis. To achieve this goal, the first step is to segment the focus from the ophthalmologic image. Former segmentation algorithms didn't consider the color ophthalmologic images' whole information, so it is unsuited to the segmentation of the cornea focus. In this paper, a novel algorithm is proposed. First the modified K-means clustering algorithm is performed on both the hue and the intensity components; then, mathematical morphological processing is used to segment cornea focus in this algorithm. Experimental results show that the algorithm is effective in segmenting the focus area of color ophthalmologic images.