An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation

Rong Xu, Jun Ohya

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In this paper, we propose an improved Kernel-based Fuzzy C-means Algorithm (iKFCM) with spatial information to reduce the effect of noise for brain MR image segmentation. We use k-nearest neighbour model and a neighbourhood controlling factor by estimating image contextual constraints to optimize the objective function of conventional KFCM method. Conventional KFCM algorithms classify each pixel in image only by its own gray value, but the proposed method classifies by the gray values of its neighbourhood system. For this reason, the proposed iKFCM has a strong robustness for image noise in image segmentation. In experiments, some synthetic grayscale images and simulated brain MR images are used to assess the performance of iKFCM in comparison with other fuzzy clustering methods. The experimental results show that the proposed iKFCM method achieves a better segmentation performance than other fuzzy clustering methods.

    Original languageEnglish
    Title of host publicationInternational Conference Image and Vision Computing New Zealand
    DOIs
    Publication statusPublished - 2010
    Event25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010 - Queenstown
    Duration: 2010 Nov 82010 Nov 9

    Other

    Other25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010
    CityQueenstown
    Period10/11/810/11/9

    Fingerprint

    Image segmentation
    Brain
    Fuzzy clustering
    Pixels
    Experiments

    Keywords

    • brain MR images
    • Fuzzy clustering
    • image segmentation
    • Kernel-based fuzzy c-means (KFCM)
    • spatial information

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Vision and Pattern Recognition
    • Electrical and Electronic Engineering

    Cite this

    An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation. / Xu, Rong; Ohya, Jun.

    International Conference Image and Vision Computing New Zealand. 2010. 6148819.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Xu, R & Ohya, J 2010, An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation. in International Conference Image and Vision Computing New Zealand., 6148819, 25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010, Queenstown, 10/11/8. https://doi.org/10.1109/IVCNZ.2010.6148819
    Xu, Rong ; Ohya, Jun. / An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation. International Conference Image and Vision Computing New Zealand. 2010.
    @inproceedings{0057cd11c56a470db8a045ba07706c1e,
    title = "An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation",
    abstract = "In this paper, we propose an improved Kernel-based Fuzzy C-means Algorithm (iKFCM) with spatial information to reduce the effect of noise for brain MR image segmentation. We use k-nearest neighbour model and a neighbourhood controlling factor by estimating image contextual constraints to optimize the objective function of conventional KFCM method. Conventional KFCM algorithms classify each pixel in image only by its own gray value, but the proposed method classifies by the gray values of its neighbourhood system. For this reason, the proposed iKFCM has a strong robustness for image noise in image segmentation. In experiments, some synthetic grayscale images and simulated brain MR images are used to assess the performance of iKFCM in comparison with other fuzzy clustering methods. The experimental results show that the proposed iKFCM method achieves a better segmentation performance than other fuzzy clustering methods.",
    keywords = "brain MR images, Fuzzy clustering, image segmentation, Kernel-based fuzzy c-means (KFCM), spatial information",
    author = "Rong Xu and Jun Ohya",
    year = "2010",
    doi = "10.1109/IVCNZ.2010.6148819",
    language = "English",
    isbn = "9781424496303",
    booktitle = "International Conference Image and Vision Computing New Zealand",

    }

    TY - GEN

    T1 - An improved Kernel-based fuzzy C-means algorithm with spatial information for brain MR image segmentation

    AU - Xu, Rong

    AU - Ohya, Jun

    PY - 2010

    Y1 - 2010

    N2 - In this paper, we propose an improved Kernel-based Fuzzy C-means Algorithm (iKFCM) with spatial information to reduce the effect of noise for brain MR image segmentation. We use k-nearest neighbour model and a neighbourhood controlling factor by estimating image contextual constraints to optimize the objective function of conventional KFCM method. Conventional KFCM algorithms classify each pixel in image only by its own gray value, but the proposed method classifies by the gray values of its neighbourhood system. For this reason, the proposed iKFCM has a strong robustness for image noise in image segmentation. In experiments, some synthetic grayscale images and simulated brain MR images are used to assess the performance of iKFCM in comparison with other fuzzy clustering methods. The experimental results show that the proposed iKFCM method achieves a better segmentation performance than other fuzzy clustering methods.

    AB - In this paper, we propose an improved Kernel-based Fuzzy C-means Algorithm (iKFCM) with spatial information to reduce the effect of noise for brain MR image segmentation. We use k-nearest neighbour model and a neighbourhood controlling factor by estimating image contextual constraints to optimize the objective function of conventional KFCM method. Conventional KFCM algorithms classify each pixel in image only by its own gray value, but the proposed method classifies by the gray values of its neighbourhood system. For this reason, the proposed iKFCM has a strong robustness for image noise in image segmentation. In experiments, some synthetic grayscale images and simulated brain MR images are used to assess the performance of iKFCM in comparison with other fuzzy clustering methods. The experimental results show that the proposed iKFCM method achieves a better segmentation performance than other fuzzy clustering methods.

    KW - brain MR images

    KW - Fuzzy clustering

    KW - image segmentation

    KW - Kernel-based fuzzy c-means (KFCM)

    KW - spatial information

    UR - http://www.scopus.com/inward/record.url?scp=84858956054&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84858956054&partnerID=8YFLogxK

    U2 - 10.1109/IVCNZ.2010.6148819

    DO - 10.1109/IVCNZ.2010.6148819

    M3 - Conference contribution

    SN - 9781424496303

    BT - International Conference Image and Vision Computing New Zealand

    ER -