|
Activity Number:
|
37
- Object-Oriented Analysis of Imaging Data
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Imaging
|
|
Abstract #303093
|
Presentation
|
|
Title:
|
Investigations on Shape Proportions and Encircled Image-Histograms
|
|
Author(s):
|
William Lamberti* and Jason M Kinser
|
|
Companies:
|
George Mason University and George Mason Univeristy
|
|
Keywords:
|
shape analysis;
low-shot learning;
classification;
images;
computer vision
|
|
Abstract:
|
In this paper, we describe new methodologies for describing and modeling digital images of shapes. A significant part of the paper will be devoted to describing a shape proportion and encircled image-histogram (SPEI, which is pronounced ‘spy’). SPEI is a shape metric which has ability to be competitive in low-shot learning classification problems where the analyst is data starved. This approach will be compared to others using a variety of models and examples.
|
Authors who are presenting talks have a * after their name.
