Technical Report CIS9708

TR#:CIS9708
Class:CIS
Title: A Layered Representation for Model-based Filtering and Recognition
Authors: Milena Salman and Michael Lindenbaum
PDFNot Available
Abstract: This work describes a new image representation, which is built over an edge map. The edges are grouped into straight line segments and properties of these segments are embedded sparsely in a three dimensional space. Specifically, the space is divided into layers and segments associated with different (quantized) orientations are placed in different layers. Therefore, we refer to this representation as to a layered representation. This representation induces an implicit correspondence relation between line segments associated with close views of the same object. Unlike grey level images, this representation satisfies the desirable local linearity/convexity property, meaning that the average of two representations of the same object, corresponding to two close views, is also an (approximate) representation of another view of the same object. An induced view-based representation of objects is a collection of image representations corresponding to their different views. Standard subspace-based methods are used to approximate this collection with Karhunen-Loeve (principal components) technique. Projection of the representation of a new, unfamiliar, image onto this subspace is used for recognition and model-based filtering. In contrast to previous subspace methods working with grey-level images this method is highly insensitive to clutter and irrelevant illumination data.
CopyrightThe above paper is copyright by the Technion, Author(s), or others. Please contact the author(s) for more information

Remark: Any link to this technical report should be to this page (http://www.cs.technion.ac.il/users/wwwb/cgi-bin/tr-info.cgi/1997/CIS/CIS9708), rather than to the URL of the PDF files directly. The latter URLs may change without notice.

To the list of the CIS technical reports of 1997
To the main CS technical reports page

Computer science department, Technion
admin