scispace - formally typeset
Open AccessDissertation

Image and Texture Analysis using Biorthogonal Angular Filter Banks

Reads0
Chats0
About
The article was published on 2004-07-09 and is currently open access. It has received 13 citations till now. The article focuses on the topics: Biorthogonal system & Image texture.

read more

Content maybe subject to copyright    Report

Image and Texture Analysis using Biorthogonal Angular
Filter Banks
A Thesis
Presented to
The Academic Faculty
by
Jose Gerardo Gonzalez Rosiles
In Partial Fulfillment
of the Requirements for the Degree
Doctor of Philosophy
School of Electrical and Computer Engineering
Georgia Institute of Technology
July 2004
Copyright
c
° 2004 by Jose Gerardo Gonzalez Rosiles

Image and Texture Analysis using Biorthogonal Angular
Filter Banks
Approved by:
Dr. Russell M. Mersereau, Committee
Chair
Dr. Mark J. T. Smith, Advisor
Dr. Mark H. Clements
Dr. James H. McClellan
Dr. A. P. Sakis Meliopoulos
Dr. Christopher Heil
School of Mathematics
Date Approved: July 6, 2004

To my mother Lucila for her unconditional love,
sacrifice, hard work and strength.
To my brother Cesar for his support and friendship.
To my daughter Paulina for the happiness she has brought to our life.
To my wife,
Laura,
for her infinite support, patience and love...
without you this work would have not been possible.
Thanks for sharing this dream.
iii

ACKNOWLEDGEMENTS
This has been a long journey for me. Over the years I met many great people that have
contributed in many ways to the completion of my Ph.D. At the end I will have more than
a title and a diploma, I will have many years of experiences and life lessons that will allow
me to move forward with a firmer walk, and as stronger and better individual. There are a
few persons that I would like to extend a personal thank you.
I would like to start by thanking the members of my thesis committee. To Dr. James
McClellan and Dr. Mark Clements, I appreciate the feedback and interest provided as
readers of this dissertation. To Dr. Russell Mersereau, I am deeply grateful for taking the
extra duties of serving as a co-advisor. I would like to thank Dr. Christoper Heil and Dr.
Sakis Meliopoulos for taking time of their schedule to attend my defense presentation.
To my advisor Dr. Mark J. T. Smith I am infinitely indebted for his support (moral
and financial), guidance and literally infinite patience in the completion of this thesis. I am
also grateful for the many professional and ethical advise he shared with me over the years.
I would like to thank the staff at CSIP, in particular Kay Gilstrap, Stacy Schultz, and
Charlote Dougthy who helped me with so many administrative issues during my residence
at CSIP. I thank Christy Ellis who took on many extra tasks at the end as I was physically
away from CSIP.
To all of the CSIP students with whom I shared illuminating discussions, a game of
soccer, a lunch, and many laughs, I give them my sincerest thanks. In particular I thank
Alen Docef, Hong Man, Paul Hong, Sang Park, Asmat Khan, Doug Britton, Joe Monaco,
Qin Jiang, and Joey Arrowood for their fellowship. To my friends Greg and Beth Showman
I thank them for the many dinners they shared with me, and to Greg for the many great
masses we played together at the Catholic Center. To my partner in crime Tami Randolph,
even though she is difficult, I hope our friendship lasts forever.
This work could not be explained without all the hands that were carrying me and
iv

pushing me over the years. First I want to thank my mother for all her unconditional
sacrifices, for the many long hours of hard work she has put over her life so that her sons
would have a better opportunity at life. Mom, I hope I have full filled your dream. To my
brother I am grateful that he took on being the “man of the house” when I left for this
adventure. I would have never done it as well as you have, thanks for taking care of our
mother and our home.
To my wife Laura, there is so much I could say that I could fill a few pages. This
dissertation would have never been completed without her support and patience, ... and
lots of pushing. Thanks for listening for hours and hours to uncomprehensible technical
concepts. Thanks for sharing this dream, and at times making it more yours than mine.
Thanks for all the free time you didn’t have with me because I was in the other room
“working on my thesis.” Thanks for all your unconditional love, I can only hope I can give
you the same back to you and our family.
Finally, I thank God for giving me the strength, faith, and hope to keep going. I thank
God for my friends and my family who never gave up on their support on this dream. I
thank God for giving me the chance and the life to reach this moment. I thank God for all
the blessings I have received over these years.
v

Citations
More filters
Journal ArticleDOI

Multidimensional Directional Filter Banks and Surfacelets

TL;DR: The proposed NDFB achieves perfect reconstruction via an iterated filter bank with a redundancy factor of N in N-D and the surfacelet transform is proposed, which can be used to efficiently capture and represent surface-like singularities in multidimensional data.
Journal ArticleDOI

An algorithm for training a large scale support vector machine for regression based on linear programming and decomposition methods

TL;DR: Experimental results demonstrate that the proposed learning scheme and the LP-SVR model are robust and efficient when compared with other methodologies for large-scale problems.

Algorithms for training large-scale linear programming support vector regression and classification

TL;DR: The main contribution of this dissertation is the development of a method to train a Support Vector Regression (SVR) model for the large-scale case where the number of training samples supersedes the computational resources.
Proceedings ArticleDOI

Rotation invariant texture classification using Bamberger pyramids

TL;DR: This work studies the application of the Bamberger directional filter bank to the problem of rotation invariant texture classification and obtains comparable classification performance to Gabor-based methods using a smaller feature set.
Proceedings ArticleDOI

Wavelet-based target detection using multiscale directional analysis

TL;DR: In this article, a target detection method that uses a special class of wavelets based on highly frequency-selective directional filter banks is proposed, which helps isolate object features in different directional filter components.
References
More filters
Journal ArticleDOI

The self-organizing map

TL;DR: The self-organizing map, an architecture suggested for artificial neural networks, is explained by presenting simulation experiments and practical applications, and an algorithm which order responses spatially is reviewed, focusing on best matching cell selection and adaptation of the weight vectors.
Journal ArticleDOI

The Laplacian Pyramid as a Compact Image Code

TL;DR: A technique for image encoding in which local operators of many scales but identical shape serve as the basis functions, which tends to enhance salient image features and is well suited for many image analysis tasks as well as for image compression.
Journal ArticleDOI

Statistical and structural approaches to texture

TL;DR: This survey reviews the image processing literature on the various approaches and models investigators have used for texture, including statistical approaches of autocorrelation function, optical transforms, digital transforms, textural edgeness, structural element, gray tone cooccurrence, run lengths, and autoregressive models.
Book

Multirate Systems and Filter Banks

TL;DR: In this paper, a review of Discrete-Time Multi-Input Multi-Output (DIMO) and Linear Phase Perfect Reconstruction (QLP) QMF banks is presented.