You are here

UCF Digital Collections ยป ETD Collection

Gradient based MRF learning for image restoration and segmentation

Download pdf | Full Screen View

Date Issued:
2012
Abstract/Description:
The undirected graphical model or Markov Random Field (MRF) is one of the more popular models used in computer vision and is the type of model with which this work is concerned. Models based on these methods have proven to be particularly useful in low-level vision systems and have led to state-of-the-art results for MRF-based systems. The research presented will describe a new discriminative training algorithm and its implementation.The MRF model will be trained by optimizing its parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. While previous work has relied on time-consuming iterative approximations or stochastic approximations, this work will demonstrate how implicit differentiation can be used to analytically differentiate the overall training loss with respect to the MRF parameters. This framework leads to an efficient, flexible learning algorithm that can be applied to a number of different models.The effectiveness of the proposed learning method will then be demonstrated by learning the parameters of two related models applied to the task of denoising images. The experimental results will demonstrate that the proposed learning algorithm is comparable and, at times, better than previous training methods applied to the same tasks.A new segmentation model will also be introduced and trained using the proposed learning method. The proposed segmentation model is based on an energy minimization framework that is novel in how it incorporates priors on the size of the segments in a way that is straightforward to implement. While other methods, such as normalized cuts, tend to produce segmentations of similar sizes, this method is able to overcome that problem and produce more realistic segmentations.
Title: Gradient based MRF learning for image restoration and segmentation.
50 views
26 downloads
Name(s): Samuel, Kegan, Author
Tappen, Marshall, Committee Chair
Da Vitoria Lobo, Niels, Committee Member
Foroosh, Hassan, Committee Member
Li, Xin, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2012
Publisher: University of Central Florida
Language(s): English
Abstract/Description: The undirected graphical model or Markov Random Field (MRF) is one of the more popular models used in computer vision and is the type of model with which this work is concerned. Models based on these methods have proven to be particularly useful in low-level vision systems and have led to state-of-the-art results for MRF-based systems. The research presented will describe a new discriminative training algorithm and its implementation.The MRF model will be trained by optimizing its parameters so that the minimum energy solution of the model is as similar as possible to the ground-truth. While previous work has relied on time-consuming iterative approximations or stochastic approximations, this work will demonstrate how implicit differentiation can be used to analytically differentiate the overall training loss with respect to the MRF parameters. This framework leads to an efficient, flexible learning algorithm that can be applied to a number of different models.The effectiveness of the proposed learning method will then be demonstrated by learning the parameters of two related models applied to the task of denoising images. The experimental results will demonstrate that the proposed learning algorithm is comparable and, at times, better than previous training methods applied to the same tasks.A new segmentation model will also be introduced and trained using the proposed learning method. The proposed segmentation model is based on an energy minimization framework that is novel in how it incorporates priors on the size of the segments in a way that is straightforward to implement. While other methods, such as normalized cuts, tend to produce segmentations of similar sizes, this method is able to overcome that problem and produce more realistic segmentations.
Identifier: CFE0004595 (IID), ucf:49207 (fedora)
Note(s): 2012-12-01
Ph.D.
Engineering and Computer Science, Computer Science
Doctoral
This record was generated from author submitted information.
Subject(s): Computer Vision -- Denoising -- Markov Random Fields -- Segmentation
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0004595
Restrictions on Access: public 2012-12-15
Host Institution: UCF

In Collections