Hybrid Models for Representation of Imagery Data

In this dissertation, we also address multimodal structures in textures by proposing a directional hybrid linear model, which combines linear hybrid models with directional filters and provides a deterministic representation of textures. Such a hybrid linear representation allows us to naturally deal with multiple textures that may appear in a single image, thus greatly facilitating texture segmentation and recognition. We discuss how this simple yet powerful representation is related to and in fact encompasses previous models in the literature, and demonstrate its applications in texture segmentation and texture recognition.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Hong, Wei

Contributors dc:contributor

• Ma, Yi

• Engineering, Electronics and Electrical

Language dc:language

eng

Identifier

(MiAaPQ)AAI3242873

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/80974