Synergy between Object Recognition and Image Segmentation Using the Expectation-Maximization Algorithm

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 31; no. 8; pp. 1486 - 1501
• Main Authors: Kokkinos, I., Maragos, P.
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.08.2009; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active appearance model; Active Appearance Models; Algorithms; Applied sciences; Artificial Intelligence; Computer science; control theory; systems; curve evolution; Equations; Evolution (biology); Exact sciences and technology; Expectation Maximization; Expectation-maximization algorithms; Face - anatomy & histology; Fitting; Fittings; generative models; Humans; Image Processing, Computer-Assisted - methods; Image reconstruction; Image segmentation; Intelligence; Iterative algorithms; Object detection; Object recognition; Pattern analysis; Pattern Recognition, Automated - methods; Pattern recognition. Digital image processing. Computational geometry; ROC Curve; Segmentation; top > down segmentation; Occlusion; Fidelity; Computer vision; curve evolution; Image recognition; top-down segmentation; Image processing; Form defect; Top down method; Active Appearance Models; generative models; Pattern recognition; Object recognition; Modeling; Image reconstruction; Image segmentation; Expectation Maximization; Model matching; Object detection; Variational calculus; EM algorithm; Occultation; Generative model
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/TPAMI.2008.158

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.