Implementation of efficient algorithms for the computation of morphological texture features /

10000XL). Parallel processing implementation on two

Bibliographic Details
Main Author: Patel, Manish J.
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1998.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:10000XL). Parallel processing implementation on two
11 based Dell 400 workstation, and SGI Power Challenge
and classification. Among texture features,
and compared. Those found efficient are then
and Dell 400 workstation) is also performed; followed
approach on an advanced DSP processor - TMS320C80.
approaches also require a considerable amount of
approaches for computing granulometry are discussed
benchmarked on three machines (Sun SPARC 20, Pentium
computation time, traditional granulometry computing
computing the granulometry texture features for
efficient ways to compute grey-scale granulometry.
elements are used. However, for many images such as
factors in the use of morphological granulometric
features. These features are increasingly being found
In many image analysis applications, objects of rographics.
interest exhibit different texture than their
interpretation. Hence, there is a need to find
investigate, and implement efficient methods of
least utilized partly due to the immense amount of
linear sub-structures. This work is an attempt to
made even greater when large images, such as
mammograms are to be analyzed. In addition to high
medical images, textures are rarely formed by hat
memory. These factors are the major restraining
morphological granulometry texture features are the
multiprocessor machines (SGI Power Challenge IOOOOXL
obtaining a granulometry. The computational problem is
scale granulometry when flat linear structuring
so when
Some fast approaches are available for computing grey-
structuring elements of any geometry are utilized in
structuring elements of any geometry. First various
surrounding areas. Texture features have been used as
the initial step towards elective image segmentation
time needed for their computation. This is especially
to be elective in applications such as medical image
Item Description:"Major subject: Electrical Engineering".
Vita.
Physical Description:xiii, 65 leaves : illustrations ; 28 cm.
Also available online.
Bibliography:Includes bibliographical references: pages 63-64.