Epitome and its applications

Due to the lack of explicit spatial consideration, the existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this thesis. Extended from the original simple graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, a new EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance based on patches and automatically cluster the spatial distribution of the similar patches. From the spatialized epitome, we present a principled (parameter-free) way of inferring the probability of a new input image under the learned model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome’s ability for discrimination on several tough vision tasks, e.g., misalignment/cross-pose face recognition, and vehicle detection with a few training samples. We also apply this model to image colorization which not only increases the visual appeal of grayscale images, but also enriches the information contained in scientific images that lack color information. Most existing methods of colorization require laborious user interaction for scribbles or image segmentation. To eliminate the need for human labor, we develop an automatic image colorization method using epitome. Built upon a generative graphical model, epitome is a condensed image appearance and shape model which also proves to be an effective summary of color information for the colorization task. We train the epitome from the reference images and perform inference in the epitome to colorize grayscale images, rendering better colorization results than previous methods.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2013

Author dc:creator

• Chu, Xinqi

Contributors dc:contributor

• Huang, Thomas S.

• colorization
• probabilistic graphical models
• image synthesis
• recognition

Statement dc:rights

• Copyright 2012 Xinqi Chu

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/42279

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/42279