Laplacian Eigenmaps [10] uses spectral techniques to perform dimensionality reduction. This technique relies on the basic assumption that the data lies in a low dimensional manifold in a high dimensional space.[11] This algorithm cannot embed out of

拉普拉斯特征映射，采用热核构造权重，是一种基于流行学习的非线性降维技术，可用于图像分割提高聚类的性能-Laplacian Eigenmap is a kind of nonlinear dimensionality reduction technique which based on manifold study, it choose the weights W using the heat kernel and it can be used for image segmentation to