Loading…

Spherical symmetric 3D local ternary patterns for natural, texture and biomedical image indexing and retrieval

In this paper, we propose a new algorithm using spherical symmetric three dimensional local ternary patterns (SS-3D-LTP) for natural, texture and biomedical image retrieval applications. The existing local binary patterns (LBP), local ternary patterns (LTP), local derivative patterns (LDP), local te...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 2015-02, Vol.149, p.1502-1514
Main Authors: Murala, Subrahmanyam, Jonathan Wu, Q.M.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a new algorithm using spherical symmetric three dimensional local ternary patterns (SS-3D-LTP) for natural, texture and biomedical image retrieval applications. The existing local binary patterns (LBP), local ternary patterns (LTP), local derivative patterns (LDP), local tetra patterns (LTrP) etc., are encode the relationship between the center pixel and its surrounding neighbors in two dimensional (2D) local region of an image. The proposed method encodes the relationship between the center pixel and its surrounding neighbors with five selected directions in 3D plane which is generated from 2D image using multiresolution Gaussian filter bank. In addition, we propose the color SS-3D-LTP (CSS-3D-LTP) where we consider the RGB spaces as three planes of 3D volume. Three experiments have been carried out for proving the worth of our algorithm for natural, texture and biomedical image retrieval applications. It is further mentioned that the databases used for natural, texture and biomedical image retrieval applications are Corel-10K, Brodatz and open access series of imaging studies (OASIS) magnetic resonance databases respectively. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to the start-of-art spatial as well as transform domain techniques on respective databases.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2014.08.042