Feature Matching with Similarity Domains Network

Feature matching is an essential step in many computer vision applications. Similarity Domains Network (SDN) is a type of Neural Networks and has been recently proposed. SDN computes multiple kernel parameters to define the decision function. In this paper, we describe how to utilize the computed ke...

Full description

Saved in:
Bibliographic Details
Published in2020 28th Signal Processing and Communications Applications Conference (SIU) pp. 1 - 4
Main Author Ozer, Sedat
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.10.2020
Subjects
Computer vision
Conferences
Feature extraction
Feature Matching with Kernel Machines
Kernel
Pattern recognition
Shape
Signal processing
Similarity Domains Network
Online AccessGet full text

Cover

More Information
Summary:Feature matching is an essential step in many computer vision applications. Similarity Domains Network (SDN) is a type of Neural Networks and has been recently proposed. SDN computes multiple kernel parameters to define the decision function. In this paper, we describe how to utilize the computed kernel parameters of SDN for feature matching. Normally, using only the distance value between the closest features does not yield good matches. However, in our experiments, we demonstrate that we can match features by using the distance value between the closest Gaussian kernel centers (also known as similarity domain centers) that are computed by SDN.
DOI:10.1109/SIU49456.2020.9302412