Scale-Driven Image Decomposition with Applications to Recognition, Registration, and Segmentation

Chen, Terrence

Permalink

https://hdl.handle.net/2142/11186 Copy

Description

Title

Scale-Driven Image Decomposition with Applications to Recognition, Registration, and Segmentation

Author(s)

Chen, Terrence

Issue Date

2006-05

Keyword(s)

computer vision

Abstract

In this paper, we propose to solve several computer vision problems using a novel fundamental idea, the scale difference between different patterns. In order to achieve our goal, we utilize the recently proposed total variation regularized L^1 functional, which has an unique geometric feature of decomposing an additive image according to scales of the patterns within the image. We analyze and study the geometric properties of the TV-L^1 model. We discuss different properties and provide intuitively proofs. We also discuss the properties when this model is applied to an image containing irregular shaped patterns, which were rarely discussed in literature. We then modify the TV-L^1 model and develop novel algorithms to solve problems in different application areas. Other than proposing the direct use of the TV-L^1 model for uneven background correction, we develop several novel algorithms based on this scale-driven image decomposition model. Our extensions and modifications are threefold: recognition, registration, and segmentation. In recognition, instead of decomposing an additive signal, we propose to factorize an image under multiplicative illumination fields based on the TV-L^1 model. The effectiveness of this factorization is validated by a significant improvement of face recognition under varying illumination. In registration, we propose a non-rigid registration framework using a novel scale hierarchy established by the TV-L^1 model. We obtain robust and accurate registration on both 2D satellite images and 3D brain MR images with this framework. At last, a probabilistic method and a multi-resolution method are used to improve the limitations of the TV-L^1 model for image segmentation. The proposed segmentation method is able to extract brain regions from head images. It can also be used to extract large scale patterns in general images. Experiment results validate the effectiveness of our work in different application areas. We believe our works have significant contributions and have brought new possibilities to computer vision, public security, surveillance, medical image analysis, and other related fields.

Type of Resource

text

Permalink

http://hdl.handle.net/2142/11186

Copyright and License Information

You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections