关键词: 人工智能, 流形学习, 缺失像素, 局部切空间对齐, 期望最大化算法

Abstract:

In context of incomplete image set, a novel EMbased Principal Component Analysis (PCA) algorithm (EMPCAM) is proposed to exploit the principal components. Then the EMPCAM is integrated seamlessly into the Local Tangent Space Alignment (LTSA) algorithm instead of standard SVD such that the modified LTSA algorithm can learn the manifold of incomplete image set. Meanwhile, in order to construct reasonable neighborhood in the presence of missing pixels, a novel distance estimation method is proposed. Extensive experiments on benchmark data sets demonstrate the effectiveness of the proposed approach.

Key words: artificial intelligence, manifold learning, missing pixels, local tangent space alignment(LTSA), EM algorithm