A Novel Context-Sensitive SVM for Classification of Remote Sensing Images

Bovolo, Francesca and Bruzzone, Lorenzo and Marconcini, Mattia and Persello, Claudio (2006) A Novel Context-Sensitive SVM for Classification of Remote Sensing Images. UNSPECIFIED. (Unpublished)

Download (221Kb) | Preview


    In this paper, a novel context-sensitive classification technique based on Support Vector Machines (CS-SVM) is proposed. This technique aims at exploiting the promising SVM method for classification of 2-D (or n-D) scenes by considering the spatial-context information of the pixel to be analyzed. In greater detail, the proposed architecture properly exploits the spatial-context information for: i) increasing the robustness of the learning procedure of SVMs to the noise present in the training set (mislabeled training samples); ii) regularizing the classification maps. The first property is achieved by introducing a context-sensitive term in the objective function to be minimized for defining the decision hyperplane in the SVM kernel space. The second property is obtained including in the classification procedure of a generic pattern the information of neighboring pixels. Experiments carried out on very high geometrical resolution images confirm the validity of the proposed technique.

    Item Type: Departmental Technical Report
    Department or Research center: Information Engineering and Computer Science
    Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885 Computer Engineering
    Report Number: DIT-06-040
    Repository staff approval on: 30 Jun 2006

    Actions (login required)

    View Item