A comparative study on feature selection for retinal vessel segmentation using FABC

Carmen Alina Lupascu, Domenico Tegolo, Emanuele Trucco

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

    18 Citations (Scopus)

    Abstract

    This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.

    Original languageEnglish
    Title of host publicationComputer Analysis of Images and Patterns, Proceedings
    Subtitle of host publication13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings
    EditorsXiaoyi Jiang, Nicolai Petkov
    Place of PublicationBerlin
    PublisherSpringer
    Pages655-662
    Number of pages8
    ISBN (Print)9783642037665
    DOIs
    Publication statusPublished - 2009
    Event13th International Conference on Computer Analysis of Images and Patterns - Munster, Germany
    Duration: 2 Sep 20094 Sep 2009
    http://cvpr.uni-muenster.de/CAIP2009/index.html

    Publication series

    NameLecture notes in computer science
    PublisherSpringer
    Volume5702

    Conference

    Conference13th International Conference on Computer Analysis of Images and Patterns
    Abbreviated titleCAIP 2009
    CountryGermany
    CityMunster
    Period2/09/094/09/09
    Internet address

    Keywords

    • Retinal images
    • vessel segmentation
    • AdaBoost classifier
    • feature selection
    • BLOOD-VESSELS
    • MATCHED-FILTERS
    • IMAGES
    • CLASSIFICATION

    Cite this

    Lupascu, C. A., Tegolo, D., & Trucco, E. (2009). A comparative study on feature selection for retinal vessel segmentation using FABC. In X. Jiang, & N. Petkov (Eds.), Computer Analysis of Images and Patterns, Proceedings: 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings (pp. 655-662). (Lecture notes in computer science; Vol. 5702). Berlin: Springer . https://doi.org/10.1007/978-3-642-03767-2_80
    Lupascu, Carmen Alina ; Tegolo, Domenico ; Trucco, Emanuele. / A comparative study on feature selection for retinal vessel segmentation using FABC. Computer Analysis of Images and Patterns, Proceedings: 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings. editor / Xiaoyi Jiang ; Nicolai Petkov. Berlin : Springer , 2009. pp. 655-662 (Lecture notes in computer science).
    @inproceedings{f0e2c51605f14441a228cd8ac905c458,
    title = "A comparative study on feature selection for retinal vessel segmentation using FABC",
    abstract = "This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.",
    keywords = "Retinal images, vessel segmentation, AdaBoost classifier, feature selection, BLOOD-VESSELS, MATCHED-FILTERS, IMAGES, CLASSIFICATION",
    author = "Lupascu, {Carmen Alina} and Domenico Tegolo and Emanuele Trucco",
    year = "2009",
    doi = "10.1007/978-3-642-03767-2_80",
    language = "English",
    isbn = "9783642037665",
    series = "Lecture notes in computer science",
    publisher = "Springer",
    pages = "655--662",
    editor = "Jiang, {Xiaoyi } and Petkov, {Nicolai }",
    booktitle = "Computer Analysis of Images and Patterns, Proceedings",

    }

    Lupascu, CA, Tegolo, D & Trucco, E 2009, A comparative study on feature selection for retinal vessel segmentation using FABC. in X Jiang & N Petkov (eds), Computer Analysis of Images and Patterns, Proceedings: 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings. Lecture notes in computer science, vol. 5702, Springer , Berlin, pp. 655-662, 13th International Conference on Computer Analysis of Images and Patterns, Munster, Germany, 2/09/09. https://doi.org/10.1007/978-3-642-03767-2_80

    A comparative study on feature selection for retinal vessel segmentation using FABC. / Lupascu, Carmen Alina; Tegolo, Domenico; Trucco, Emanuele.

    Computer Analysis of Images and Patterns, Proceedings: 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings. ed. / Xiaoyi Jiang; Nicolai Petkov. Berlin : Springer , 2009. p. 655-662 (Lecture notes in computer science; Vol. 5702).

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

    TY - GEN

    T1 - A comparative study on feature selection for retinal vessel segmentation using FABC

    AU - Lupascu, Carmen Alina

    AU - Tegolo, Domenico

    AU - Trucco, Emanuele

    PY - 2009

    Y1 - 2009

    N2 - This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.

    AB - This paper presents a comparative study on five feature selection heuristics applied to a retinal image database called DRIVE. Features are chosen from a feature vector (encoding local information, but as well information from structures and shapes available in the image) constructed for each pixel in the field of view (FOV) of the image. After selecting the most discriminatory features, an AdaBoost classifier is applied for training. The results of classifications are used to compare the effectiveness of the five feature selection methods.

    KW - Retinal images

    KW - vessel segmentation

    KW - AdaBoost classifier

    KW - feature selection

    KW - BLOOD-VESSELS

    KW - MATCHED-FILTERS

    KW - IMAGES

    KW - CLASSIFICATION

    U2 - 10.1007/978-3-642-03767-2_80

    DO - 10.1007/978-3-642-03767-2_80

    M3 - Conference contribution

    SN - 9783642037665

    T3 - Lecture notes in computer science

    SP - 655

    EP - 662

    BT - Computer Analysis of Images and Patterns, Proceedings

    A2 - Jiang, Xiaoyi

    A2 - Petkov, Nicolai

    PB - Springer

    CY - Berlin

    ER -

    Lupascu CA, Tegolo D, Trucco E. A comparative study on feature selection for retinal vessel segmentation using FABC. In Jiang X, Petkov N, editors, Computer Analysis of Images and Patterns, Proceedings: 13th International Conference, CAIP 2009, Münster, Germany, September 2-4, 2009. Proceedings. Berlin: Springer . 2009. p. 655-662. (Lecture notes in computer science). https://doi.org/10.1007/978-3-642-03767-2_80