Image outlier detection and feature extraction via L1-norm-based 2D probabilistic PCA

Fujiao Ju, Yanfeng Sun, Junbin Gao, Yongli Hu, Baocai Yin

    Research output: Contribution to journalArticlepeer-review

    50 Citations (Scopus)
    4 Downloads (Pure)


    This paper introduces an L1-norm-based probabilistic principal component analysis model on 2D data (L1-2DPPCA) based on the assumption of the Laplacian noise model. The Laplacian or L1 density function can be expressed as a superposition of an infinite number of Gaussian distributions. Under this expression, a Bayesian inference can be established based on the variational expectation maximization approach. All the key parameters in the probabilistic model can be learned by the proposed variational algorithm. It has experimentally been demonstrated that the newly introduced hidden variables in the superposition can serve as an effective indicator for data outliers. Experiments on some publicly available databases show that the performance of L1-2DPPCA has largely been improved after identifying and removing sample outliers, resulting in more accurate image reconstruction than the existing PCA-based methods. The performance of feature extraction of the proposed method generally outperforms other existing algorithms in terms of reconstruction errors and classification accuracy
    Original languageEnglish
    Pages (from-to)4834-4846
    Number of pages13
    JournalIEEE Transactions on Image Processing
    Issue number12
    Publication statusPublished - Dec 2015


    Dive into the research topics of 'Image outlier detection and feature extraction via L1-norm-based 2D probabilistic PCA'. Together they form a unique fingerprint.

    Cite this