一种基于AEP和K主曲线的图像分割方法

广泛应用的第一主成分是对数据集的一维线性最优描述,主曲线是第一主成分的非线性推广.在此提出了一种基于AEP和K主曲线的图像分割方法,将统计学中的主曲线很好地应用于图像处理.该方法首先将腐蚀传播算法和区域生长型分水岭方法相结合,标记出图像中不同物体并产生初始边缘;然后,用K主曲线多边形线算法进行边缘点连接.实验结果证明,AEP算法能标记出一幅图中不同的目标,K主曲线能提供精确的目标轮廓线,该分割方法行之有效.

An image segmentation method based on AEP and K principal curves

The first linear principal component is the optimal linear 1-d summarization of the data. Principal curves are nonlinear generalizations of the first linear principal component. Proposed is a new image segmentation method based on AEP and the K principal curves, which apply the statistical principal curves to image processing. Adopted first is the advanced erosion-propagation (AEP) algorithm which combines the erosion-propagation algorithm and the region-growing version of watershed algorithm to classify the original image and label, producing the initial information of edge. Then, according to the information of edge, the method links the edges of the objects using the polygonal line algorithm of K principal curves. Experimental results prove that the AEP algorithm can label the distinct objects in the image and that K principal curves can provide accurate contours. The method is very effectual.