Eigenimage - Based Robust Image Segmentation Using Level Sets

This thesis presents a novel way of integrating shape prior information into a level set based segmentation scheme. It utilizes the eigenimages of the signed-distance functions of the training shapes and confines the segmentation to statistically allowable shapes while minimizing the Chan-Vese functional via gradient descent. Implemented under the level set framework, the resulting algorithm can handle topo-logical changes very well and is robust to noise and initial contour location due to the prior shape information being integrated. Meanwhile, the compactness of the eigenimage representation overcomes the " curse of dimensionality problem " existing for one-dimensional principal component analysis. We demonstrate this technique by applying it to several synthetic and real images. For my loving wife, as thanks for enduring my many long hours at the computer and nights I wasn't able to come home to you. Acknowledgments I would like to thank my adviser, Dr. Jundong Liu, for his continual support during my time as a student here, my family, for being an encouragement and an inspiration, and my God, for endowing me with the intellect which has made all of this possible. Thank you.