Scale space clustering evolution for salient region detection on 3D deformable shapes

Xupeng Wang, Ferdous Sohel, Mohammed Bennamoun, Yulan Guo, Hang Lei

    Research output: Contribution to journalArticle

    1 Citation (Scopus)

    Abstract

    Salient region detection without prior knowledge is a challenging task, especially for 3D deformable shapes. This paper presents a novel framework that relies on clustering of a data set derived from the scale space of the auto diffusion function. It consists of three major techniques: scalar field construction, shape segmentation initialization and salient region detection. We define the scalar field using the auto diffusion function at consecutive time scales to reveal shape features. Initial segmentation of a shape is obtained using persistence-based clustering, which is performed on the scalar field at a large time scale to capture the global shape structure. We propose two measures to assess the clustering both on a global and local level using persistent homology. From these measures, salient regions are detected during the evolution of the scalar field. Experimental results on three popular datasets demonstrate the superior performance of the proposed framework in region detection.

    Original languageEnglish
    Pages (from-to)414-427
    Number of pages14
    JournalPattern Recognition
    Volume71
    DOIs
    Publication statusPublished - 1 Nov 2017

    Cite this

    @article{386f519946104b91aa4e44ee4e40b1cf,
    title = "Scale space clustering evolution for salient region detection on 3D deformable shapes",
    abstract = "Salient region detection without prior knowledge is a challenging task, especially for 3D deformable shapes. This paper presents a novel framework that relies on clustering of a data set derived from the scale space of the auto diffusion function. It consists of three major techniques: scalar field construction, shape segmentation initialization and salient region detection. We define the scalar field using the auto diffusion function at consecutive time scales to reveal shape features. Initial segmentation of a shape is obtained using persistence-based clustering, which is performed on the scalar field at a large time scale to capture the global shape structure. We propose two measures to assess the clustering both on a global and local level using persistent homology. From these measures, salient regions are detected during the evolution of the scalar field. Experimental results on three popular datasets demonstrate the superior performance of the proposed framework in region detection.",
    keywords = "Clustering algorithm, Deformable shape segmentation, Diffusion geometry, Persistent homology, Salient region detection",
    author = "Xupeng Wang and Ferdous Sohel and Mohammed Bennamoun and Yulan Guo and Hang Lei",
    year = "2017",
    month = "11",
    day = "1",
    doi = "10.1016/j.patcog.2017.05.018",
    language = "English",
    volume = "71",
    pages = "414--427",
    journal = "Pattern Recognition",
    issn = "0031-3203",
    publisher = "Elsevier",

    }

    Scale space clustering evolution for salient region detection on 3D deformable shapes. / Wang, Xupeng; Sohel, Ferdous; Bennamoun, Mohammed; Guo, Yulan; Lei, Hang.

    In: Pattern Recognition, Vol. 71, 01.11.2017, p. 414-427.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Scale space clustering evolution for salient region detection on 3D deformable shapes

    AU - Wang, Xupeng

    AU - Sohel, Ferdous

    AU - Bennamoun, Mohammed

    AU - Guo, Yulan

    AU - Lei, Hang

    PY - 2017/11/1

    Y1 - 2017/11/1

    N2 - Salient region detection without prior knowledge is a challenging task, especially for 3D deformable shapes. This paper presents a novel framework that relies on clustering of a data set derived from the scale space of the auto diffusion function. It consists of three major techniques: scalar field construction, shape segmentation initialization and salient region detection. We define the scalar field using the auto diffusion function at consecutive time scales to reveal shape features. Initial segmentation of a shape is obtained using persistence-based clustering, which is performed on the scalar field at a large time scale to capture the global shape structure. We propose two measures to assess the clustering both on a global and local level using persistent homology. From these measures, salient regions are detected during the evolution of the scalar field. Experimental results on three popular datasets demonstrate the superior performance of the proposed framework in region detection.

    AB - Salient region detection without prior knowledge is a challenging task, especially for 3D deformable shapes. This paper presents a novel framework that relies on clustering of a data set derived from the scale space of the auto diffusion function. It consists of three major techniques: scalar field construction, shape segmentation initialization and salient region detection. We define the scalar field using the auto diffusion function at consecutive time scales to reveal shape features. Initial segmentation of a shape is obtained using persistence-based clustering, which is performed on the scalar field at a large time scale to capture the global shape structure. We propose two measures to assess the clustering both on a global and local level using persistent homology. From these measures, salient regions are detected during the evolution of the scalar field. Experimental results on three popular datasets demonstrate the superior performance of the proposed framework in region detection.

    KW - Clustering algorithm

    KW - Deformable shape segmentation

    KW - Diffusion geometry

    KW - Persistent homology

    KW - Salient region detection

    UR - http://www.scopus.com/inward/record.url?scp=85019837337&partnerID=8YFLogxK

    U2 - 10.1016/j.patcog.2017.05.018

    DO - 10.1016/j.patcog.2017.05.018

    M3 - Article

    VL - 71

    SP - 414

    EP - 427

    JO - Pattern Recognition

    JF - Pattern Recognition

    SN - 0031-3203

    ER -