You are here

Dictionary Learning for Image Analysis

Download pdf | Full Screen View

Date Issued:
2013
Abstract/Description:
In this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows:1) We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning.2) Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by embedding dictionary learning into Conditional Random Field (CRF) learning. We demonstrate that such smoothness constraints can lead to state-of-the-art performance for pixel-classification tasks.3) Finally, we lay down the foundations of super-latent learning. By treating sparse codes on a CRF as latent variables, dictionary learning can also be performed via the Latent (Structural) SVM formulation for jointly learning a classifier over the sparse codes. The dictionary is treated as a super-latent variable that generates the latent variables.
Title: Dictionary Learning for Image Analysis.
11 views
4 downloads
Name(s): Khan, Muhammad Nazar, Author
Tappen, Marshall, Committee Chair
Foroosh, Hassan, Committee Member
Stanley, Kenneth, Committee Member
Li, Xin, Committee Member
University of Central Florida, Degree Grantor
Type of Resource: text
Date Issued: 2013
Publisher: University of Central Florida
Language(s): English
Abstract/Description: In this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows:1) We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning.2) Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by embedding dictionary learning into Conditional Random Field (CRF) learning. We demonstrate that such smoothness constraints can lead to state-of-the-art performance for pixel-classification tasks.3) Finally, we lay down the foundations of super-latent learning. By treating sparse codes on a CRF as latent variables, dictionary learning can also be performed via the Latent (Structural) SVM formulation for jointly learning a classifier over the sparse codes. The dictionary is treated as a super-latent variable that generates the latent variables.
Identifier: CFE0004701 (IID), ucf:49844 (fedora)
Note(s): 2013-05-01
Ph.D.
Engineering and Computer Science, Computer Science
Doctoral
This record was generated from author submitted information.
Subject(s): Dictionary Learning -- Sparse Coding -- Discriminative -- Reconstruction-Discrimination Tradeoff -- Spatial Prior -- Latent
Persistent Link to This Record: http://purl.flvc.org/ucf/fd/CFE0004701
Restrictions on Access: public 2013-05-15
Host Institution: UCF

In Collections