Dissertation Announcement for Stanton Price
01/24/18 at 10:00 AM
January 11, 2018
Faculty, graduate and undergraduate students,
You are cordially invited to my dissertation defense.
Title: Fusion of evolution constructed features for computer vision
When: Wednesday, January 24, 2018 at 10:00 AM
Where: Simrall Hall, Room 228 (Conference Room)
Candidate: Stanton R. Price
Degree: Doctor of Philosophy, Electrical and Computer Engineering
Committee:
Dr. John E. Ball
(Major Professor)
Dr. Derek T. Anderson
(Co-major Professor)
Dr. J. Patrick Donohoe
(Committee Member)
Dr. Nicolas H. Younan
(Committee Member)
Abstract:
In this dissertation, image feature extraction quality is enhanced through the introduction of two feature learning techniques and, subsequently, feature-level fusion strategies are presented that improve classification performance. Two image/signal processing techniques are defined for pre-conditioning image data such that the discriminatory information is highlighted for improved feature extraction. The fi rst approach, improved Evolution-COnstructed features, employs a modified genetic algorithm to learn a series of image transforms, specific to a given feature descriptor, for enhanced feature extraction. The second method, Genetic prOgramming Optimal Feature Descriptor (GOOFeD), is a genetic programming-based approach to learning the transformations of the data for feature extraction. GOOFeD offers a very rich and expressive solution space due to is ability to represent highly complex compositions of image transforms through binary, unary, and/or the combination of the two, operators. Regardless of the two techniques employed, the goal of each is to learn a composition of image transforms from training data to present a given feature descriptor with the best opportunity to extract its information for the application at hand. Next , feature-level fusion via multiple kernel learning (MKL) is utilized to better combine the features extracted and, ultimately, improve classification accuracy performance. MKL is advanced through the introduction of six new indices for kernel weight assignment. Five of the indices are measured directly from the kernel matrix proximity values, making them highly efficient to compute. The calculation of the sixth index is performed explicitly on distributions in the reproducing kernel Hilbert space. The proposed techniques are applied to an automatic buried explosive hazard detection application and significant results are achieved.
Cheers,
-Stanton