In this work we show how to combine bottom-up and topdown approaches into a single figure-ground segmentation process. This process provides accurate delineation of object boundaries that cannot be achieved by either the topdown or bottom-up approach alone. The top-down approach uses object representation learned from examples to detect an object in a given input image and provide an approximation to its figure-ground segmentation. The bottomup approach uses image-based criteria to define coherent groups of pixels that are likely to belong together to either the figure or the background part. The combination provides a final segmentation that draws on the relative merits of both approaches: The result is as close as possible to the top-down approximation, but is also constrained by the bottom-up process to be consistent with significant image discontinuities. We construct a global cost function that represents these top-down and bottom-up requirements. We then show how the global minimum of this function can be efficiently found by applying the sum-product algorithm. This algorithm also provides a confidence map that can be used to identify image regions where additional top-down or bottom-up information may further improve the segmentation. Our experiments show that the results derived from the algorithm are superior to results given by a pure top-down or pure bottom-up approach. The scheme has broad applicability, enabling the combined use of a range of existing bottom-up and top-down segmentations. 1.

Abstract. Bottom-up approaches, which rely mainly on continuity principles, are often insufficient to form accurate segments in natural images. In order to improve performance, recent methods have begun to incorporate top-down cues, or object information, into segmentation. In this paper, we propose an approach to utilizing category-based information in segmentation, through a formulation as an image labelling problem. Our approach exploits bottom-up image cues to create an over-segmented representation of an image. The segments are then merged by assigning labels that correspond to the object category. The model is trained on a database of images, and is designed to be modular: it learns a number of image contexts, which simplify training and extend the range of object classes and image database size that the system can handle. The learning method estimates model parameters by maximizing a lower bound of the data likelihood. We examine performance on three real-world image databases, and compare our system to a standard classifier and other conditional random field approaches, as well as a bottom-up segmentation method. 1

We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects. 1.

This article proposes a technique to animate a Chinese style painting given its image. We first extract descriptions of the brush strokes that hypothetically produced it. The key to the extraction process is the use of a brush stroke library, which is obtained by digitizing single brush strokes drawn by an experienced artist. The steps in our extraction technique are first to segment the input image, then to find the best set of brush strokes that fit the regions, and, finally, to refine these strokes to account for local appearance. We model a single brush stroke using its skeleton and contour, and we characterize texture variation within each stroke by sampling perpendicularly along its skeleton. Once these brush descriptions have been obtained, the painting can be animated at the brush stroke level. In this article, we focus on Chinese paintings with relatively sparse strokes. The animation is produced using a graphical application we developed. We present several animations of real paintings using our technique.

I would like to thank the people who have helped and supported me in completing this work. First of all I would like to thank my supervisor Dr. Mongi Abidi for his support, patience, and guidance during these years of my study at UTK. Also, I would like to thank the other members of my dissertation committee, Dr. Collins, Dr. Koch, Dr. Qi, and Dr. Roberts, for their interests in this work and their insightful advice to this dissertation. I am very grateful to Dr. Koschan and Dr. Paik for their invaluable suggestions to my research and this dissertation. Special thanks to Dr. David Page for our inspiring conversations and his many helpful comments on this dissertation. I would also like to thank the faculty, staff and students in the IRIS laboratory who created an excellent environment where I have enjoyed working. I am indebted to Vicki Courtney-Smith for her helping with my various administrative needs, to Mark Mitckes for his proofreading of my outgoing documents, and to the fellow students including Brad Grinstead, Umayal Chidambaram, Tak Motoyama, Justin Acuff and many others for their kind help. Last but not least, I want to express gratitude to my family. Thanks to my parents Mingyu Zhang and Shuiyue Xu for their consistent support during these academic years. Huge thanks

is permitted for educational or research use on condition that this copyright notice is included in any copy. Publications in the FI MU Report Series are in general accessible via WWW: