CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2009 vol.31 Issue No.08 - August
Synergy between Object Recognition and Image Segmentation Using the Expectation-Maximization Algorithm
Issue No.08 - August (2009 vol.31)
Iasonas Kokkinos , University of California at Los Angeles, Los Angeles
Petros Maragos , National Technical University of Athens, Athens
In this work, we formulate the interaction between image segmentation and object recognition in the framework of the Expectation-Maximization (EM) algorithm. We consider segmentation as the assignment of image observations to object hypotheses and phrase it as the E-step, while the M-step amounts to fitting the object models to the observations. These two tasks are performed iteratively, thereby simultaneously segmenting an image and reconstructing it in terms of objects. We model objects using Active Appearance Models (AAMs) as they capture both shape and appearance variation. During the E-step, the fidelity of the AAM predictions to the image is used to decide about assigning observations to the object. For this, we propose two top-down segmentation algorithms. The first starts with an oversegmentation of the image and then softly assigns image segments to objects, as in the common setting of EM. The second uses curve evolution to minimize a criterion derived from the variational interpretation of EM and introduces AAMs as shape priors. For the M-step, we derive AAM fitting equations that accommodate segmentation information, thereby allowing for the automated treatment of occlusions. Apart from top-down segmentation results, we provide systematic experiments on object detection that validate the merits of our joint segmentation and recognition approach.
Image segmentation, object recognition, Expectation Maximization, Active Appearance Models, curve evolution, top--down segmentation, generative models.
Iasonas Kokkinos, Petros Maragos, "Synergy between Object Recognition and Image Segmentation Using the Expectation-Maximization Algorithm", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 8, pp. 1486-1501, August 2009, doi:10.1109/TPAMI.2008.158