Multiscale Particle Filter through Contour Detection Framework

We focus on the edgelets by detecting the algorithm by joining two small pieces of edges through contour detection. Bayesian modeling focus on multiscale edgelets which is embeds semi-local information. Prior and distributions can be seen offline with the help of shape database. One can see the following features online like integrate color and gradient information via local, textural, oriented, and profile gradient-based features for understanding and comparing. The underlying model is estimated using a sequential Monte Carlo approach, and the final soft contour detection map is retrieved from the approximated trajectory distribution. We also propose to extend the model to the interactive cut-out task. Experiments conducted on the Berkeley Segmentation data sets show that the proposed MultiScale Particle Filter Contour Detector method performs well compared to competing state-of-the-art methods.