In this paper, we present a novel object detection scheme that uses information of the sample fragments. These sample fragments are extracted by decomposition of the sample contour. Then, the candidate fragments corresponding to the sample fragments are detected from the images by partial Hausdorff distance. The Multiclass Discriminative Field (MDF) is used to select the most probable fragments from candidate fragments. The parameter estimation and inference of the MDF are simplified by using the candidate fragments as nodes of a graph. With these selected fragments, the contours of the objects can be obtained. The experiments on our postmark database and the ETHZ database show the feasibility of our proposed scheme. © 2011 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Zhang, X., Sun, Q., & Lu, Y. (2011). Object detection based on multiclass discriminative field. In Advances in Intelligent and Soft Computing (Vol. 122, pp. 495–500). https://doi.org/10.1007/978-3-642-25664-6_58
Mendeley helps you to discover research relevant for your work.