IRREGULAR-STRUCTURE TREE MODELS FOR IMAGE INTERPRETATION By SINISA TODOROVIC A DISSERTATION PRESENTED TO THE GRADUATE SCHOOL OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY

of Dissertation Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy IRREGULAR-STRUCTURE TREE MODELS FOR IMAGE INTERPRETATION By Sinisa Todorovic May 2005 Chair: Dapeng Wu Major Department: Electrical and Computer Engineering In this dissertation, we seek to accomplish the following related goals: (1) to find a unifying framework to address localization, detection, and recognition of objects, as three sub-tasks of image-interpretation, and (2) to find a computationally efficient and reliable solution to recognition of multiple, partially occluded, alike objects in a given single image. The second problem is to date an open problem in computer vision, eluding a satisfactory solution. For this purpose, we formulate object recognition as Bayesian estimation, whereby class labels with the maximum posterior distribution are assigned to each pixel. To efficiently estimate the posterior distribution of image classes, we propose to model images with graphical models known as irregular trees. The irregular tree specifies probability distributions over both its structure and image classes. This means that, for each image, it is necessary to infer the optimal model structure, as well as the posterior distribution of image classes. We propose several inference algorithms as a solution to this NP-hard problem (nondeterministic polynomial time), which can be viewed as variants of the Expectation-Maximization (EM) algorithm. After inference, the model represents a forest of subtrees, each of which segments the image. That is, inference of model structure provides a solution to object localization and detection.