University of Houston
Department of Computer Science

In partial fulfillment of the Requirements for the Degree of
Master of Science


Jin Li
will defend her thesis

Texture Based Segmentation




Abstract

Visual texture is a property of a region in an image that is independent of the color and brightness of the region. It is one of the important characteristics used in identifying objects and regions of interests in an image. Texture analysis forms the basis of object recognition and segmentation in several domains. The scheme of texture-based segmentation is usually conceptualized as two modular processes: 1) feature computation, and 2) segmentation of homogeneous regions based on the feature values.

In this thesis, we examine two texture analysis methods that are used widely. These are the gray level co-occurrence matrix method and the Laws’ texture energy method. We present results from applying these two methods on a variety of images.

Date: Tuesday, December 3, 2002
Time: 1:15 PM
Place: 550-PGH



Faculty, students, and the general public are invited.
Thesis Advisor: Dr. Kakadiaris