Information Technology Reference
In-Depth Information
Chapter 14
3D Object Classification and Segmentation
Methods
Martin Žagar, Mario Kovač, Josip Knezović, Hrvoje Mlinarić,
and Daniel Hofman *
Abstract. Future multimedia high-quality systems will be, among all, based on
improving 3D visual experience. To raise 3D visual content quality and interactiv-
ity it is necessary to enable segmentation and classification of content which in-
volves dividing the scene into meaningful sub-regions with the same attributes.
Partitioning the image into grouping objects has various different applications in a
wide variety of areas, since distinctive features in raw images may appear unclear
to the human eyes. Segmentation can be defined as the identification of meaning-
ful image components. It is a fundamental task in image processing providing the
basis for any kind of further high-level image analysis. There are many different
ways of segmenting the 3D image, all of which can be considered as a good seg-
mentations, depending on objects of interest on an image, and to a large extent, the
user's own subjectivity. Key issues in this chapter include different techniques for
segmentation of 3D object based on classification on different regions and shapes.
1 Introduction
In segmentation of an image, it is important to define the image features which
will be the basis for segmentation. The term image feature refers to two possible
entities: a global property of an image (e.g. the average grey level, an area in a
voxel global feature); or a part of the image with some special properties (e.g. a
circle, a line, or a textured region in an intensity image, a planar surface in a range
image local feature). 3D image segmentation is, however, a difficult process, as it
depends on a wide variety of factors such as the complexity of image content, the
objects of interest or the number of classes required. While one mode of grouping
may successfully segment the image into meaningful sub-regions, the same mode
Search WWH ::




Custom Search